Not in the top 1,000 by GitHub stars
Parth1811/JevFlow
A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.
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
plugin/skills/jevflow/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
ef6563f6d425 → ef6563f6d425
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → ef6563f6d425
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit ef6563f6d425de36984f87478c5b6c9ff41cd487
git clone --filter=blob:none --no-checkout https://github.com/Parth1811/JevFlow.git .hotskills/parth1811-jevflow && git -C .hotskills/parth1811-jevflow checkout --detach ef6563f6d425de36984f87478c5b6c9ff41cd487
# Copy each selected skill directory from .hotskills/parth1811-jevflow into .claude/skills/<skill-name>/12GitHub stars
0stars in 7 days
1skill in this repository
11commits in 30 days
Heat
1.6- 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
- jevflow
plugin/skills/jevflow
How it works
jevflow
When your agent uses it
How to work inside a Jevflow-tracked session. Use when a Jevflow context block or a "[jevflow]" Stop instruction appears, when the user asks to keep a long task on track toward a goal, or when they mention flow.json, phases, or the Jevflow supervisor.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
1,014 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
- When a `[jevflow]` instruction blocks your stop
- Starting and checking
- Working alongside other agents
- What Jev sees
- Optional tool gates (off by default)
- Dynamic phases and side effects
Scripts executed separately
../../../examples/spike/plugin/hooks/block_once.sh../../../examples/spike/plugin/hooks/log_hook.sh
Files
../../../.claude-plugin/marketplace.jsonasset418 bytes../../../examples/spike/plugin/.claude-plugin/plugin.jsonasset98 bytes../../../examples/spike/plugin/hooks/block_once.shruns315 bytes../../../examples/spike/plugin/hooks/hooks.jsonasset948 bytes../../../examples/spike/plugin/hooks/hooks.jsonasset948 bytes../../../examples/spike/plugin/hooks/hooks.jsonasset948 bytes../../../examples/spike/plugin/hooks/hooks.jsonasset948 bytes../../../examples/spike/plugin/hooks/hooks.jsonasset948 bytes../../../examples/spike/plugin/hooks/log_hook.shruns209 bytes../../.claude-plugin/icon.svgasset1,018 bytes../../.claude-plugin/plugin.jsonasset1,577 bytes../../hooks/hooks.jsonasset1,972 bytesSKILL.mdcore4,263 bytes
Read SKILL.md
# Working with Jevflow
Jevflow tracks a session against a flow in `.jevflow/flow.json`: a goal and ordered phases, each with a `done_when` sentence and often a shell `check`. When you try to stop, a Stop hook runs the checks, asks Jev (a calibrated judgment model) where the work is, and a fixed policy decides whether you may stop.
## When a `[jevflow]` instruction blocks your stop
- Treat it as the next instruction. Do the concrete thing it names for the named phase.
- If it quotes failing check output, fix the cause shown there. Run the check command yourself before claiming the phase is done.
- "You said the work is done, but it is not" means a check still fails. Do not repeat the claim; make the check pass.
- "You are looping" means your last approach is not working. Re-read the goal and change approach, not just parameters.
- "Regression" means a phase that was done now fails its check. Fix that first.
- Never edit `.jevflow/state.json` or `.jevflow/flow.json` to get past a block. Only Jevflow code writes state. Changing the flow is a user decision.
## Starting and checkingSkills included
- jevflow
Repository facts
- License
- MIT
- Created
- Sep 24, 2026
- Last pushed
- Oct 25, 2026
- Forks
- 0
- Open issues
- 0
- 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 4 notes
examples/spike/plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedexamples/spike/plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedexamples/spike/plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedexamples/spike/plugin/hooks/hooks.json:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 5 network referencesin 2 files: plugin/.claude-plugin/plugin.json:17 plugin/.claude-plugin/icon.svg:1
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: examples/spike/plugin/hooks/block_once.sh:1 examples/spike/plugin/hooks/log_hook.sh:1
- 2 references to secretsin 1 file: plugin/.claude-plugin/plugin.json:22
- No requests to vote in Hot
Show all 9 signals by file
examples/spike/plugin/hooks/block_once.sh
- Executable scriptline 1
#!/bin/sh
examples/spike/plugin/hooks/log_hook.sh
- Executable scriptline 1
#!/bin/sh
plugin/.claude-plugin/icon.svg
- Network accessline 1
<svg xmlns="http://www.w3.org/2000/svg" width="256" height="256" viewBox="0 0 256 256" role="img" aria-label="Jevflow">
plugin/.claude-plugin/plugin.json
- Network accessline 17
"name": "Parth Patil" }, "homepage": "https://github.com/Parth1811/JevFlow", - Network accessline 18
}, "homepage": "https://github.com/Parth1811/JevFlow", "repository": "https://github.com/Parth1811/JevFlow", - Network accessline 19
"homepage": "https://github.com/Parth1811/JevFlow", - Network accessline 20
"repository": "https://github.com/Parth1811/JevFlow", - Access to secretsline 22
[Credential-related source omitted] - Access to secretsline 38
[Credential-related source omitted]
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: 2 facts
- Executable script in code of a file that runsexamples/spike/plugin/hooks/block_once.sh:1High confidence
- Executable script in code of a file that runsexamples/spike/plugin/hooks/log_hook.sh: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 plugin/skills/jevflow/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugin/skills/jevflow/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugin/skills/jevflow/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugin/skills/jevflow/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugin/skills/jevflow/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.
