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/wan-huiyan/agent-traffic-control/git-amend-hits-async-post-commit-hook-commitnpx skills add wan-huiyan/agent-traffic-control --skill git-amend-hits-async-post-commit-hook-commitgit clone --depth 1 https://github.com/wan-huiyan/agent-traffic-controlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/git-amend-hits-async-post-commit-hook-commit)<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/git-amend-hits-async-post-commit-hook-commit"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/git-amend-hits-async-post-commit-hook-commit.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00184 | $0.01040 |
| Opus 5 | $0.00092 | $0.00520 |
| Sonnet 5 | $0.00037 | $0.00208 |
| Haiku 4.5 | $0.00018 | $0.00104 |
Grade A, and why
git-amend-hits-async-post-commit-hook-commit 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 3d ago.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git commit --amend hits the async post-commit hook's commit
Problem
A repo has an async post-commit hook — it fires in the background after a
commit and creates its OWN follow-up commit (auto-generated docs, a site
regen, a changelog or plan-checkbox tick). If you (or a subagent) run
git commit --amend after that hook has fired, --amend rewrites the
hook's commit, not your work commit. Your change's content is folded into a
commit titled e.g. [auto-docs] ...; your real feat(...) commit is left
untouched. The amend "succeeds" — no error — so it is easy to miss.
Context / Trigger Conditions
- The repo has a background/async post-commit hook (look for a
post-commithook that backgrounds work, or commits with prefixes like[auto-docs],chore: regenerate site, etc. appearing without a human authoring them). - You ran
git commit, then latergit commit --amend(often a code-review fix, a typo fix, or "tidy the last commit"). git logshows HEAD's message is the hook's, not yours — and your change is inside that hook commit.- Especially common in subagent-driven development: a fix subagent is told
to
--amendits fix, but the async hook committed between the implementer subagent's commit and the fix subagent running.
Solution
- Never
git commit --amendin a repo with an async post-commit hook — and never instruct a subagent to. Use a freshgit commit. A clean extra commit is harmless (it squash-merges away); a misplaced--amendis silent structural corruption. - Re-read
git logyourself after every commit. Do not trust an agent-reported SHA — the async hook shifts HEAD after the agent reports. Determine BASE/HEAD for the next step by readinggit log --oneline. - If you genuinely must amend: first confirm HEAD is YOUR commit
(
git log -1 --format='%s'), and ideally disable the hook for the operation.
Verification
git log --oneline -3 immediately after committing — confirm your commit
message sits on the commit you intend, and note any [auto-docs] / regen
commit the hook added on top.
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.
- 3d ago First seen · 84 lines · 184 tokens per session scan A d9f8660ab099
git-amend-hits-async-post-commit-hook-commit is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 17d ago), licensed MIT. It adds 184 tokens to every session and 1,040 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
misuzu
Respond to PR review comments semi-automatically. Fetches all review threads and comments, splits them into logical units, fixes and commits one unit at a time, then replies and resolves review threads. Use when the user wants to address PR review feedback or respond to review comments.
commit-style
Commit message style guidelines. Use when writing or proposing git commit messages, including direct git commit commands outside the /commit skill.
bridge
Join a shared per-project chat between AI coding agents (Claude Code, Cursor, …) — group channels + DMs — and receive messages from other instances using whatever your agent supports (push, loop, or poll). Use when coordinating multiple agent instances on the same project.
codex-coplan
Bring in an external model (Codex) to co-develop a plan — both models draft independently, align on disagreements, and merge into one plan. Load this only when the user explicitly names Codex (e.g. "let's discuss this with Codex," "what does Codex think about this approach") — don't auto-trigger just because a plan…
loop-implement
Close a single implementation task with a methodology-grounded verification loop — define done, analyze, plan, write tests first (Red), implement (Green), run, self-review, get an independent test-quality audit, then judge against done; on failure reflect and retry (bounded). Use for one non-trivial task (feature…
codex-orchestrator
Delegate execution tasks to Codex (Claude plans and reviews). Load this only when the user names Codex explicitly — no matter how big the task is, if the user hasn't mentioned Codex, do it yourself.