Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/onedro1d/dark-factory/commit-syncnpx skills add OneDro1d/dark-factory --skill commit-syncgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00072 | $0.01023 |
| Opus 5 | $0.00036 | $0.00511 |
| Sonnet 5 | $0.00014 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00102 |
Grade A, and why
commit-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commit-sync
Goal: never let code and the knowledge layer drift apart, and never push junk or secrets. One procedure: sync → message → confirm → commit → push.
Step 1 — Review what changed
git status --porcelain
git diff --stat
git diff # actually read it
Identify which services/contracts/agents/skills the change touches.
Step 2 — Sync the knowledge layer (the "update skills and agents" part)
The
pre-commitstaleness gate (.claude/hooks/pre-commit) enforces the structural floor automatically — it will block the commit if a contract/ schema/service or an agent/skill changed without its map/README staged. This step is how you satisfy that gate, plus the semantic part it can't check (findings/ decisions). Don't rely on--no-verifyto skip it.
Apply the context-management skill (knowledge-keeper discipline). For this diff:
- Contract/routing-key/table/object-store-key changed → update the shared-models index
CLAUDE.md+ the serviceCLAUDE.md+.claude/context/SERVICE-MAP.md+.claude/context/DATA-FLOW.md(nodes/authority/rules if the data shape or ownership moved). - A bug fixed / root cause confirmed → update its
F-###in.claude/context/FINDINGS.md(status OPEN→FIXED, add the fixing commit). - A design decision made → add a
D-###to.claude/context/DECISIONS.md. - An agent or skill added/removed/renamed → update
.claude/agents/README.md(routing table) so it stays the source of truth. - A
CLAUDE.mdclaim the diff makes stale → fix it, cite the code. Only touch what this change actually affects. Cite sources; no guessing.
Step 3 — Safety gate (block on any hit)
git diff --cached -U0 | grep -nEi 'api[_-]?key|secret|password|token|sk-ant|BEGIN .*PRIVATE KEY|bearer ' || echo "no obvious secrets"
Also confirm no PII in fixtures/data. If anything trips, STOP and report — do not commit.
Step 4 — Handle the gitignored knowledge files
If .claude/** and new CLAUDE.md files are gitignored in this repo, and the user wants them shared, force-add explicitly and say so:
git add -f .claude/agents .claude/skills .claude/context <service>/CLAUDE.md
Otherwise leave them local. Never silently change .gitignore — flag it and let the user decide.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 80 lines · 72 tokens per session scan A 8fa9eebde25a
commit-sync is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,023 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…