Borrowing it
Nothing to install: this file belongs to adrienm7/ergopti. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adrienm7/ergopti/main/.agents/skills/implement-audit-findings/SKILL.mdgit clone --depth 1 https://github.com/adrienm7/ergoptiWrote 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/adrienm7/ergopti/implement-audit-findings)<a href="https://agentmods.dev/skills/adrienm7/ergopti/implement-audit-findings"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/implement-audit-findings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adrienm7/ergopti/implement-audit-findings"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/implement-audit-findings.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.00929 |
| Opus 5.5 | $0.00029 | $0.00372 |
| Sonnet 5.5 | $0.00015 | $0.00186 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
implement-audit-findings 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 15d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement driver audit findings
Turn a validated audit manifest into independently reviewable local commits. The manifest is the queue; do not create a second narrative plan unless the user asks for one. Never push, merge, stash, clean, reset, move a worktree, or modify the main checkout's unrelated files.
Select and validate the audit
Use the report the user named, otherwise the newest strict dated directory for the requested scope:
node tools/audit/workflow.cjs validate-report --report <findings.json>
node tools/audit/workflow.cjs preflight --scope <ahk|hammerspoon>
node tools/audit/workflow.cjs status --report <findings.json>
Canonical worktrees are sibling directories named from the repository:
<repo>-fix-ahk and <repo>-fix-hs. preflight recognizes an already
registered worktree and reports it as resumable. It never creates or modifies
one. If the canonical path is absent but another active worktree owns a branch
for that scope, stop; do not create a duplicate or migrate it implicitly.
When preflight returns missing, first verify that its exact expected_path
is absent and that the intended branch name does not already exist. Then create
that one worktree from the manifest's audited_sha with an OS-neutral Git
command:
git worktree add -b fix/<ahk|hammerspoon>-audit-<YYYY-MM-DD> <expected_path> <audited_sha>
Run preflight again and continue only when it reports ready. An existing
branch, directory, competing worktree, or different base is user state: inspect
and stop rather than deleting, resetting, force-creating, or silently reusing
it.
An existing dirty canonical worktree is not disposable clutter. Inspect its branch and diffs and map them to a finding before editing. If ownership is ambiguous or changes span findings, report that state and stop. Never use stash as a shortcut: stashes are repository-global and these worktrees are active.
Implement one finding
Read windows-toolchain, verify-change, ship-fix, commit-and-push, and the
matching driver skill. Add cross-driver-parity, i18n, logger, or
meta-test only when the finding touches those surfaces.
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.
- 15d ago First seen · 88 lines · 73 tokens per session scan A a95af43dea10
implement-audit-findings is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 929 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
observability-langsmith
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.