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 skills add chen3feng/agent-skills --skill check-git-log-before-refixgit clone --depth 1 https://github.com/chen3feng/agent-skillsWrote 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/chen3feng/agent-skills/check-git-log-before-refix)<a href="https://agentmods.dev/skills/chen3feng/agent-skills/check-git-log-before-refix"><img src="https://agentmods.dev/badge/skills/chen3feng/agent-skills/check-git-log-before-refix.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 5.1 | $0.00037 | $0.01345 |
| Opus 5 | $0.00018 | $0.00673 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
check-git-log-before-refix 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 8d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check git log before re-fixing
When to use
The user reports an error that looks identical to something you (or another agent) recently fixed. Typical signals:
- The same error message you just worked on yesterday.
- The user says "it still fails" after you thought you landed a fix.
- You're on a feature branch that was cut before the fix merged.
- A teammate / another agent has been editing the same repo in parallel.
Before you write a single new line of code, stop and check whether the fix is already on the default branch and you just aren't looking at it.
Problem
Agents — and humans in a hurry — default to "I see an error, I write a
patch." When the fix already exists on main/master but you're on a
stale branch or a dirty working tree, that default makes things worse:
- You re-invent a worse version of the existing fix.
- You layer a wrong patch on top of a right one that's hidden by an uncommitted edit or an un-pulled commit.
- You open a PR that either duplicates an already-merged PR or, more embarrassingly, conflicts with it.
The concrete failure mode that motivated this skill:
- PR-A lands a correct fix for error E on
main. - An agent is still checked out on a feature branch cut before PR-A.
- User re-runs the scenario, still sees E (because the feature branch predates the fix).
- Agent "diagnoses" E again, invents a new — and wrong — patch, and sometimes even leaves it as uncommitted changes that silently revert the real fix on the next merge.
Solution
Before modifying anything, run this short check:
-
Check working tree and branch first.
git status git branch --show-current git log --oneline -5If there are uncommitted changes in the file that "still has the bug", that is a huge red flag — previous agent output may have reverted a real fix locally.
-
Grep the history for the symptom. Use a keyword from the error message or the affected file:
git log --oneline --all --grep="AutomationCommandlet" git log --oneline --all -- path/to/affected_file
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.
- 8d ago First seen · 154 lines · 37 tokens per session scan A b1c33b3160ea
check-git-log-before-refix is a skill published in the GitHub repository chen3feng/agent-skills (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 1,345 once invoked, about $0.0002 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
fix-issue
Fetch un GitHub issue por número, entiende el problema, localiza el código, implementa fix mínimo y commitea referenciando el issue.
debugging-executions
Debug failed or wrong-output workflow executions using executions tools. Load when the user reports execution failures, unexpected node output, empty parameter values after a successful run, or a node showing a red or failed expression error.
comet-github-issue-fix
A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.
flow-next-land
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
auto-repo-setup
Diagnose, repair, and standardize repository setup and safe Git workflows for Claude Code or Codex. Use when a repository will not run, a collaborator is onboarding, dependencies or credentials are missing, the user wants startup sync, SessionStart output is duplicated, project instructions or hooks need auditing, or…