Not in the top 1,000 by GitHub stars
addyosmani/factory
A reference software factory 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
template/.agents/skills/factory-implement/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-monitor/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-spec/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-status/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-triage/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-tune/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.agents/skills/factory-verify/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.claude/skills/factory-implement/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.claude/skills/factory-monitor/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.claude/skills/factory-spec/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.claude/skills/factory-triage/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
template/.claude/skills/factory-verify/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 8af116567166
No earlier version was observed for comparison.
Verified commit 8af116567166a0a16588b7ab1b9934ece0b775bc
git clone --filter=blob:none --no-checkout https://github.com/addyosmani/factory.git .hotskills/addyosmani-factory && git -C .hotskills/addyosmani-factory checkout --detach 8af116567166a0a16588b7ab1b9934ece0b775bc
# Copy each selected skill directory from .hotskills/addyosmani-factory into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/addyosmani/factory.git .hotskills/addyosmani-factory && git -C .hotskills/addyosmani-factory checkout --detach 8af116567166a0a16588b7ab1b9934ece0b775bc
# Copy each selected skill directory from .hotskills/addyosmani-factory into .agents/skills/<skill-name>/Heat
6.4- 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
- factory-implement
template/.agents/skills/factory-implement - factory-monitor
template/.agents/skills/factory-monitor - factory-spec
template/.agents/skills/factory-spec - factory-status
template/.agents/skills/factory-status - factory-triage
template/.agents/skills/factory-triage - factory-tune
template/.agents/skills/factory-tune - factory-verify
template/.agents/skills/factory-verify - factory-implement
template/.claude/skills/factory-implement - factory-monitor
template/.claude/skills/factory-monitor - factory-spec
template/.claude/skills/factory-spec - factory-triage
template/.claude/skills/factory-triage - factory-verify
template/.claude/skills/factory-verify
How it works
factory-implement
When your agent uses it
Claim and implement one ready GitHub issue, run fail-closed gates, obtain independent verification, and open a draft pull request.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
117 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
Files
SKILL.mdcore505 bytes
Read SKILL.md
# Factory implementation for Codex
Read `docs/factory/CONTRACT.md`, `docs/factory/CHARTER.md`, and then the canonical workflow
in `.claude/skills/factory-implement/SKILL.md`. Use Codex's subagent mechanism for the fresh
verifier context. If an independent context is unavailable, stop before opening a non-draft
pull request.
View the complete source on GitHubfactory-monitor
When your agent uses it
Inspect factory health, stale work, CI, security advisories, and recent run evidence without implementing fixes.
What it loads into context
Frontmatter
28 tokensAlways available to the agent
SKILL.md
91 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
Files
SKILL.mdcore393 bytes
Read SKILL.md
# Factory monitoring for Codex
Read `docs/factory/CONTRACT.md`, `docs/factory/CHARTER.md`, and then the canonical workflow
in `.claude/skills/factory-monitor/SKILL.md`. Write a unique run record rather than appending
to shared state.
View the complete source on GitHubfactory-spec
When your agent uses it
Turn an ambiguous factory issue into human-approved product, behavior, design, and implementation slices. Use interactively before implementation.
What it loads into context
Frontmatter
31 tokensAlways available to the agent
SKILL.md
103 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
Files
SKILL.mdcore476 bytes
Read SKILL.md
# Factory specification for Codex
Read `docs/factory/CONTRACT.md`, `docs/factory/CHARTER.md`, and then the canonical workflow
in `.claude/skills/factory-spec/SKILL.md`. Keep every human approval gate interactive. Use a
fresh subagent for the critic pass when the workflow requires one.
View the complete source on GitHubfactory-status
When your agent uses it
Show the factory control room from live GitHub labels, open PRs, recent run records, gate health, and charter limits.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
98 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
Files
SKILL.mdcore424 bytes
Read SKILL.md
# Factory status for Codex
Read `docs/factory/CONTRACT.md`, then follow the report workflow in
`.claude/commands/factory.md`. Live GitHub labels and PRs outrank the Markdown snapshots.
This skill reports only; it never merges, approves, labels, or closes work.
View the complete source on GitHubfactory-triage
When your agent uses it
Classify GitHub issues into the factory's live label queue and write an auditable snapshot. Use for backlog triage or a scheduled triage run.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
121 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
Files
SKILL.mdcore473 bytes
Read SKILL.md
# Factory triage for Codex
Read `docs/factory/CONTRACT.md`, `docs/factory/CHARTER.md`, and then the canonical workflow
in `.claude/skills/factory-triage/SKILL.md`. Follow that workflow using the tools available
in Codex. GitHub labels are the live queue; `QUEUE.md` is only a snapshot.
View the complete source on GitHubfactory-tune
When your agent uses it
Review factory evidence and propose tighter or looser constraints without editing the charter. Use for a periodic constraint review.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
96 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
Files
SKILL.mdcore436 bytes
Read SKILL.md
# Factory tuning for Codex
Read `docs/factory/CONTRACT.md`, then follow `.claude/commands/factory-tune.md`. Propose
changes and record accepted human decisions in `docs/factory/DECISIONS.md`; never edit the
charter or gate requirements on your own initiative.
View the complete source on GitHubfactory-verify
When your agent uses it
Independently verify a factory pull request, including fail-closed gates, negative test proof, scope, and load-bearing review.
What it loads into context
Frontmatter
33 tokensAlways available to the agent
SKILL.md
111 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
Files
SKILL.mdcore469 bytes
Read SKILL.md
# Factory PR verification for Codex
Read `docs/factory/CONTRACT.md`, `docs/factory/CHARTER.md`, and then the canonical workflow
in `.claude/skills/factory-verify/SKILL.md`. Use a fresh subagent for any critic pass and the
shared `.factory/scripts/prove-test.sh` procedure for negative test proof.
View the complete source on GitHubfactory-implement
When your agent uses it
Claim one live GitHub queue item, implement it end to end, run fail-closed gates and independent verification, then open a draft PR. Use for one ready-to-implement issue or the implementation routine.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,673 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
- Before writing any code
- Branch
- Implementing
- Gates
- Independent verification
- Pull request
- What you never do
Files
SKILL.mdcore7,151 bytesSKILL.mdcore7,151 bytesSKILL.mdcore7,151 bytesSKILL.mdcore7,151 bytes
Read SKILL.md
# Factory implementation
You implement **exactly one queue item per run**. Not two. If you finish early, stop.
Batching items is how a single wrong assumption becomes a wide diff nobody can review.
## Before writing any code
1. Read `docs/factory/CONTRACT.md`, then `docs/factory/CHARTER.md`.
2. Query GitHub for open issues labeled `factory:ready-to-implement`. The live label is
authoritative; read the latest `factory-handoff:v1` comment for `done_when`, expected
files, gate level, and confidence. `QUEUE.md` is only a snapshot. If the handoff is
missing, duplicated, malformed, or inconsistent with the charter, move the issue to
`factory:needs-info` and stop. If running locally without GitHub access, stop unless aView the complete source on GitHubfactory-monitor
When your agent uses it
Scheduled health sweep that closes the factory loop - reads CI failures, recent commits, dependency and security advisories, and live queue labels, then files issues and writes an immutable run record. Use for the nightly or weekly monitor routine.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
1,031 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
- Sweep
- Filing
- Report
- What you never do
Files
SKILL.mdcore4,543 bytesSKILL.mdcore4,543 bytes
Read SKILL.md
# Factory monitor
This is the stage that closes the loop. Without it a factory only processes work a human
remembered to file, which means the backlog reflects attention rather than reality.
**You file issues. You do not fix anything.** Mixing detection and repair in one run means
a bad detection becomes a bad commit before anyone sees it.
Read `docs/factory/CONTRACT.md` and `docs/factory/CHARTER.md` first.
## Sweep
Run each of these. Where a check is not applicable to this repo, say so rather than
silently skipping it.View the complete source on GitHubfactory-spec
When your agent uses it
Turn a ready-to-spec queue item into an approved plan through explicit human gates. Use when an item needs scope decided before code exists, when planning a feature, or before starting a migration. Runs interactively - not for unattended routines.
What it loads into context
Frontmatter
54 tokensAlways available to the agent
SKILL.md
1,160 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
- Gates
- Status file
- For migrations specifically
Files
SKILL.mdcore4,951 bytes
Read SKILL.md
# Factory spec
This skill exists because the cheapest place to fix a decision is before any code encodes
it. Once a model has written a thousand lines, changing direction is expensive and every
instinct is to patch instead.
**This skill is interactive.** It stops and waits for a human. Do not run it inside an
unattended routine; a routine that approves its own spec has no gates at all.
Read `docs/factory/CONTRACT.md` and `docs/factory/CHARTER.md` before gate 1.
## Gates
Four, in order. Stop at each one. Never merge two gates into a single pass. Never proceedView the complete source on GitHubfactory-triage
When your agent uses it
Classify incoming issues into the live GitHub label queue, reproduce where cheap, and write an auditable QUEUE.md snapshot. Use when triaging a backlog, running the scheduled triage routine, or deciding what the factory should pick up next.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
1,422 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
- Before anything
- Gathering work
- Reproduction
- Classification
- Writing a queue entry
- Labelling
- Ending the run
Files
SKILL.mdcore5,995 bytes
Read SKILL.md
# Factory triage
You are the intake stage. Your output is a **sorted queue and a shortlist for a human**,
never merged code. You do not write implementation code in this skill.
## Before anything
1. Read `docs/factory/CONTRACT.md`, then `docs/factory/CHARTER.md`. The charter defines the tier, what is automatable, and what is
load-bearing. **If the charter does not cover an item, the answer is `needs-info`, not
a guess.** Silence in the charter means stop.
2. Query GitHub issue labels for current state. `docs/factory/QUEUE.md` is a snapshot and
may lag while a triage PR is open. Do not use it to override a live label.
## Gathering workView the complete source on GitHubfactory-verify
When your agent uses it
Verify an open factory PR before human review - re-runs gates, checks the test proves the fix, checks scope and test tampering. Use when reviewing a factory PR, running the PR review routine, or asked to independently check a change.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
707 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
- Procedure
- Reporting
- What this is for, and what it is not
- Standing bias
Files
SKILL.mdcore3,037 bytes
Read SKILL.md
# Factory verify
Use this when a PR already exists and you are the check standing between it and a human.
For verification during implementation, the `factory-verifier` subagent is the right tool;
this skill is the PR-level version and can be driven by a GitHub-triggered routine.
## Procedure
1. Read `docs/factory/CONTRACT.md`, then `docs/factory/CHARTER.md` for the tier,
load-bearing globs, and definition of done.
2. Check out the PR branch.
3. Run the required gate level yourself. Do not trust the `FACTORY_GATES` line in the PR
body; produce your own and compare. A mismatch is the finding.
4. Run the checks the deterministic gates cannot make:View the complete source on GitHubSkills included
- factory-implement
- factory-monitor
- factory-spec
- factory-status
- factory-triage
- factory-tune
- factory-verify
- factory-implement
- factory-monitor
- factory-spec
- factory-triage
- factory-verify
Repository facts
- License
- MIT
- Created
- Aug 18, 2026
- Last pushed
- Aug 21, 2026
- Forks
- 21
- Open issues
- 2
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
template/.claude/skills/factory-implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplate/.claude/skills/factory-implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplate/.claude/skills/factory-implement/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedtemplate/.claude/skills/factory-monitor/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 3 network referencesin 1 file: factory-triage/SKILL.md:68
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 3 signals by file
template/.claude/skills/factory-triage/SKILL.md
- Network accessline 68
## FQ-<issue-number>: <title> - disposition: ready-to-implement - source: https://github.com/<owner>/<repo>/issues/<n> - Network accessline 69
- disposition: ready-to-implement - source: https://github.com/<owner>/<repo>/issues/<n> - last_triaged: 2026-08-16 - Network accessline 70
- source: https://github.com/<owner>/<repo>/issues/<n>
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: 3 facts
- Network access in code of the SKILL.mdfactory-triage/SKILL.md:68High confidence
- Network access in code of the SKILL.mdfactory-triage/SKILL.md:69High confidence
- Network access in code of the SKILL.mdfactory-triage/SKILL.md:70High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Path CLAUDE.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md template/.agents/skills/factory-implement/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md template/.agents/skills/factory-implement/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md template/.agents/skills/factory-implement/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md template/.agents/skills/factory-implement/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.