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/ship-fix/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/ship-fix)<a href="https://agentmods.dev/skills/adrienm7/ergopti/ship-fix"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/ship-fix/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/ship-fix"><img src="https://agentmods.dev/badge/skills/adrienm7/ergopti/ship-fix.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 | $0.00025 | $0.01066 |
| Opus 5.5 | $0.00010 | $0.00426 |
| Sonnet 5.5 | $0.00005 | $0.00213 |
| Haiku 4.5 | $0.00003 | $0.00107 |
Grade A, and why
ship-fix 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipping a fix
No fix is complete until its regression test is written, runs, and is green.
This is the repository delivery contract in AGENTS.md.
1. Before touching code
Read docs/memory/README.md, then the one topic for the area you are about to
change. It is the
in-repo record of foot-guns and invariants that have already bitten this
codebase; several "new" bugs are documented recurrences. See the
project-memory skill.
2. Fix the root cause
Find why the failure is possible, not just where it surfaces. A fix that makes the symptom disappear while leaving the mechanism intact will regress under a slightly different trigger.
Ask explicitly: why was this silent until now? A bug that produced no log,
no error, no visible failure usually means a swallowed exception or a missing
guard — that silence is itself a second bug worth fixing under the fail-fast
contract in AGENTS.md.
Check whether the same mistake exists at sibling call sites. Per
project-ahk-invariant-incomplete-application in
docs/memory/windows-ahk.md, the recurring pattern here is the ONE missed
sibling site — audit the whole class.
3. Write the regression test
It must fail before the fix and pass after it. Write and run the targeted test before editing production code whenever possible. Never stash, reset, or rewrite an active worktree to manufacture pre-fix evidence. If production code was already edited, use a recorded pre-fix reproduction or baseline; otherwise state the evidence gap explicitly and make the regression assertion as direct as possible.
Put a stable slug in the test name ((perf-2026-07-21),
(llm-cancel-under-critical)) so --only can replay exactly that case in
seconds instead of the whole suite.
Read the failure message when it goes red. If it fails for a reason other than the bug — a missing constant, a typo in a symbol name — the test is not yet encoding the root cause.
Put it in the suite covering the affected layer:
| Layer | Location |
|---|---|
| Windows AHK driver | static/ergopti_plus/windows/tests/ (unit/, meta/, startup/, e2e/) |
| macOS Hammerspoon | static/ergopti_plus/macos/tests/ |
| Cross-platform / JS | tools/test/ |
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 · 104 lines · 25 tokens per session scan A 7a978e886217
ship-fix is a skill published in the GitHub repository adrienm7/ergopti (14 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,066 once invoked, about $0.0001 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.