Not in the top 1,000 by GitHub stars
FlorianBruniaux/flow-lean
Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude Code and Codex.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-contract-preparation-2026-10-23-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-contract-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-guardrail-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-guardrail-preparation-2026-10-24-portable-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-guardrail-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-reference-qualification-2026-10-22-evidence/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-requalification-2026-10-22-evidence/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
skills/flow-lean/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 2305869f9d6c
No earlier version was observed for comparison.
Verified commit 2305869f9d6cc3e2bfdc95b317be0f996d942daf
git clone --filter=blob:none --no-checkout https://github.com/FlorianBruniaux/flow-lean.git .hotskills/florianbruniaux-flow-lean && git -C .hotskills/florianbruniaux-flow-lean checkout --detach 2305869f9d6cc3e2bfdc95b317be0f996d942daf
# Copy each selected skill directory from .hotskills/florianbruniaux-flow-lean into .claude/skills/<skill-name>/Heat
4.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- flow-lean
evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean - flow-lean
evals/results/pr2-contract-preparation-2026-10-23-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-contract-qualification-2026-10-24-evidence/sources/skills/flow-lean - flow-lean
evals/results/pr2-guardrail-preparation-2026-10-24-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-guardrail-preparation-2026-10-24-portable-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-guardrail-qualification-2026-10-24-evidence/sources/skills/flow-lean - flow-lean
evals/results/pr2-reference-qualification-2026-10-22-evidence/sources/skills/flow-lean - flow-lean
evals/results/pr2-requalification-2026-10-22-evidence/sources/skills/flow-lean - flow-lean
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/skill - flow-lean
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/skill - flow-lean
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/sources/skills/flow-lean - flow-lean
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/skill - flow-lean
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/sources/skills/flow-lean - flow-lean
skills/flow-lean
How it works
flow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,140 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
../../../../../../.claude-plugin/marketplace.jsonasset546 bytes../../../../../../.claude-plugin/plugin.jsonasset262 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,140 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesSKILL.mdcore24,572 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
4,968 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore23,734 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
4,968 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore23,734 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
4,816 tokensWhen the skill is activated
Reference documents
750 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore22,964 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc3,780 bytesscripts/rollback_reference.pyruns8,440 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
4,459 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Files
SKILL.mdcore21,170 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
903 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed safeguards
- Density
- Code changes
- Presentation
- Completion reports
- Controls
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore4,861 bytesSKILL.mdcore4,861 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
## Fixed safeguards
Preserve supplied facts, actors, recipients, conditions, negations, quantities and uncertainty. Resolve quoted pronouns from their speaker and addressee. Permission is not a promise; assigning someone an action does not establish their agreement. A condition says nothing about its current fulfillment. Retain ambiguity when the source leaves it unresolved. Before sending, remove unsupported changes to actor, modality or evidence scope.
Separate observations from hypotheses. Use supplied evidence; request only the missing diagnostic that can change the decision. A test outcome alone does not identify an unseen cause. Verify optional exact claims or omit them. Never invent execution, approval, citations or independent review. Report tests only at their tested scope; leave only the relevant unknown unresolved. No uncalibrated duration or savings claims. Done when each factual claim is supplied, verified or explicitly bounded.
Work within existing authorization and finish its required scope. Preserve unrelated work, trust-boundary validation and decision-changing risks. Keep diagnostics in authorized operator channels, with secrets redacted. Inspect state and obtain any missing authorization before consequential changes. Do not weaken access controls to diagnose a fault. Proposed code must include the inputs, prerequisites and checks needed to use it safely; do not claim it was executed.
For rollback, require trusted original and installation postimages, external writer exclusion throughout check/restore/verify, and evidence outside removed paths. Never recapture changed targets as expected postimages. Validate every backup and target before mutation; any missing, changed, linked or wrong-type target stops the operation. Preserve metadata, foreign locks, unexpected temporary files and concurrent edits; remove new files only if unchanged and directories only if empty. An error code does not prove no mutation. Report actual state and retained receipts. Read the bundled [bounded rollback contract](references/rollback.md) before adapting its reference; if unavailable, obtain its contents before claiming compatibility. Test the declared runtime, failures and cleanup before claiming the implementation works.
## Density
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
903 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed safeguards
- Density
- Code changes
- Presentation
- Completion reports
- Controls
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore4,861 bytesSKILL.mdcore4,861 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
## Fixed safeguards
Preserve supplied facts, actors, recipients, conditions, negations, quantities and uncertainty. Resolve quoted pronouns from their speaker and addressee. Permission is not a promise; assigning someone an action does not establish their agreement. A condition says nothing about its current fulfillment. Retain ambiguity when the source leaves it unresolved. Before sending, remove unsupported changes to actor, modality or evidence scope.
Separate observations from hypotheses. Use supplied evidence; request only the missing diagnostic that can change the decision. A test outcome alone does not identify an unseen cause. Verify optional exact claims or omit them. Never invent execution, approval, citations or independent review. Report tests only at their tested scope; leave only the relevant unknown unresolved. No uncalibrated duration or savings claims. Done when each factual claim is supplied, verified or explicitly bounded.
Work within existing authorization and finish its required scope. Preserve unrelated work, trust-boundary validation and decision-changing risks. Keep diagnostics in authorized operator channels, with secrets redacted. Inspect state and obtain any missing authorization before consequential changes. Do not weaken access controls to diagnose a fault. Proposed code must include the inputs, prerequisites and checks needed to use it safely; do not claim it was executed.
For rollback, require trusted original and installation postimages, external writer exclusion throughout check/restore/verify, and evidence outside removed paths. Never recapture changed targets as expected postimages. Validate every backup and target before mutation; any missing, changed, linked or wrong-type target stops the operation. Preserve metadata, foreign locks, unexpected temporary files and concurrent edits; remove new files only if unchanged and directories only if empty. An error code does not prove no mutation. Report actual state and retained receipts. Read the bundled [bounded rollback contract](references/rollback.md) before adapting its reference; if unavailable, obtain its contents before claiming compatibility. Test the declared runtime, failures and cleanup before claiming the implementation works.
## Density
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
903 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Fixed safeguards
- Density
- Code changes
- Presentation
- Completion reports
- Controls
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore4,861 bytesSKILL.mdcore4,861 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
## Fixed safeguards
Preserve supplied facts, actors, recipients, conditions, negations, quantities and uncertainty. Resolve quoted pronouns from their speaker and addressee. Permission is not a promise; assigning someone an action does not establish their agreement. A condition says nothing about its current fulfillment. Retain ambiguity when the source leaves it unresolved. Before sending, remove unsupported changes to actor, modality or evidence scope.
Separate observations from hypotheses. Use supplied evidence; request only the missing diagnostic that can change the decision. A test outcome alone does not identify an unseen cause. Verify optional exact claims or omit them. Never invent execution, approval, citations or independent review. Report tests only at their tested scope; leave only the relevant unknown unresolved. No uncalibrated duration or savings claims. Done when each factual claim is supplied, verified or explicitly bounded.
Work within existing authorization and finish its required scope. Preserve unrelated work, trust-boundary validation and decision-changing risks. Keep diagnostics in authorized operator channels, with secrets redacted. Inspect state and obtain any missing authorization before consequential changes. Do not weaken access controls to diagnose a fault. Proposed code must include the inputs, prerequisites and checks needed to use it safely; do not claim it was executed.
For rollback, require trusted original and installation postimages, external writer exclusion throughout check/restore/verify, and evidence outside removed paths. Never recapture changed targets as expected postimages. Validate every backup and target before mutation; any missing, changed, linked or wrong-type target stops the operation. Preserve metadata, foreign locks, unexpected temporary files and concurrent edits; remove new files only if unchanged and directories only if empty. An error code does not prove no mutation. Report actual state and retained receipts. Read the bundled [bounded rollback contract](references/rollback.md) before adapting its reference; if unavailable, obtain its contents before claiming compatibility. Test the declared runtime, failures and cleanup before claiming the implementation works.
## Density
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubflow-lean
When your agent uses it
Use when the user explicitly asks for Flow Lean, lean or less verbose output, action-first responses, expansion of a compressed Flow Lean answer, or Flow Lean recap and skills-footer controls.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
5,339 tokensWhen the skill is activated
Reference documents
834 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Persistence
- Layer 1: Solution altitude (ponytail)
- Layer 2: Form (action-first)
- Layer 3: Density (caveman)
- Two honesty-safe overrides
- Review depth
- Adapt depth to the request
- Levels
- Never
- Anti-AI markers (two tiers)
- Examples
Scripts executed separately
scripts/rollback_reference.py
Files
SKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesSKILL.mdcore25,698 bytesevals/scenarios.jsonasset2,815 bytesreferences/rollback.mddoc4,234 bytesscripts/rollback_reference.pyruns8,716 bytes
Read SKILL.md
# Flow Lean
Minimal solution, action-first shape, zero-fat density. Keep only required
context, action, decision-changing risk, or proof.
## Persistence
Mode state: enabled after invocation. Disable with "stop flow-lean" or "normal mode".
Default: **concise**. Switch with `/flow-lean concise|detailed|ultra`.
Compatibility aliases: `full` = `concise`; `lite` = `detailed`. "More detail"
selects `detailed` for the current response.
## Layer 1: Solution altitude (ponytail)
View the complete source on GitHubSkills included
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
- flow-lean
Repository facts
- License
- MIT
- Created
- Jul 27, 2026
- Last pushed
- Oct 25, 2026
- Forks
- 1
- Open issues
- 2
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 25 notes
evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-preparation-2026-10-24-portable-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-preparation-2026-10-24-portable-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-guardrail-qualification-2026-10-24-evidence/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-finalization-2026-10-24-plan/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-finalization-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-finalization-2026-10-24-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/skill/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedevals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/sources/skills/flow-lean/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 8 network referencesin 2 files: .claude-plugin/marketplace.json:1 .claude-plugin/plugin.json:5
- No hidden or obfuscated text
- No instruction overrides
- 15 executable scriptsin 15 files: flow-lean/scripts/rollback_reference.py:1 flow-lean/scripts/rollback_reference.py:1 flow-lean/scripts/rollback_reference.py:1 and 12 more
- No access to secrets
- No requests to vote in Hot
Show all 23 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 2
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", - Network accessline 5
"owner": { "name": "Florian Bruniaux", "url": "https://github.com/FlorianBruniaux" - Network accessline 6
"name": "Florian Bruniaux", "url": "https://github.com/FlorianBruniaux" }, - Network accessline 7
"url": "https://github.com/FlorianBruniaux"
.claude-plugin/plugin.json
evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-actor-qualification-2026-10-24-evidence/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-contract-preparation-2026-10-23-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-contract-qualification-2026-10-24-evidence/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-guardrail-preparation-2026-10-24-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-guardrail-preparation-2026-10-24-portable-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-guardrail-qualification-2026-10-24-evidence/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-reference-qualification-2026-10-22-evidence/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/skill/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-finalization-2026-10-24-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/skill/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-preparation-2026-10-24-final-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/skill/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
evals/results/pr2-v4-ablation-preparation-2026-10-24-plan/sources/skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/flow-lean/scripts/rollback_reference.py
- Executable scriptline 1
#!/usr/bin/env python3
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 15 facts
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsskill/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsskill/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsskill/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
- Executable script in code of a file that runsflow-lean/scripts/rollback_reference.py:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md evals/results/pr2-actor-preparation-2026-10-24-plan/sources/skills/flow-lean/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.