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 woliveiras/geremmyas --skill bugfixgit clone --depth 1 https://github.com/woliveiras/geremmyasWrote 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/woliveiras/geremmyas/bugfix)<a href="https://agentmods.dev/skills/woliveiras/geremmyas/bugfix"><img src="https://agentmods.dev/badge/skills/woliveiras/geremmyas/bugfix.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 | $0.00041 | $0.00918 |
| Opus 5 | $0.00020 | $0.00459 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
bugfix 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bugfix
Fix bugs by building evidence before changing code. Use the bundled regression testing reference when converting the reproduction into a durable test.
Document Location
Save bugfix documents under:
docs/bugfixes/YYYY-MM-DD-<bug-slug>.md
Use the local date when the investigation starts. The slug must be lowercase kebab-case, based on the user-visible symptom or failing capability, for example:
docs/bugfixes/2026-05-21-login-redirect-loop.md
If a relevant bugfix document already exists, update it instead of creating a duplicate. If the bug has an issue, ticket, or PR reference, put that reference inside the document, not in the filename.
For outages, save the postmortem separately under:
docs/postmortems/YYYY-MM-DD-<incident-slug>.md
Process
- Create or update a bugfix document with:
- symptom
- impact
- reproduction steps
- expected behavior
- actual behavior
- outage status When creating one, use the focused bugfix document template.
- Build a reproduction loop before changing production code. Prefer a failing test, then an HTTP/CLI/browser script, then a small harness.
- Confirm the loop reproduces the user's bug, not a nearby failure.
- Write 3-5 ranked hypotheses. Each hypothesis must predict what evidence would confirm or falsify it.
- Instrument only the boundary needed to test the current hypothesis. Tag any temporary logs clearly so they can be removed.
- Convert the minimized reproduction into a regression test at the correct seam (mandatory before applying the fix).
- Run the regression test and record its expected failure before changing production code. A test that starts green is not regression evidence; correct the seam or reproduction first.
- Apply the smallest change that addresses the highest-ranked hypothesis supported by evidence.
- Rerun the regression test, original reproduction loop, and nearest relevant suite. If evidence falsifies the hypothesis, update the document, rank the remaining hypotheses, and start another evidence-driven cycle.
- Remove temporary instrumentation, record the actual cause and why the fix addresses it, and capture any residual evidence that could not be automated or run locally.
- Escalate only when the requested objective must materially expand, production or external authority is required, or the same blocker remains after three consecutive evidence-driven cycles. Otherwise continue autonomously.
- If the bug was an outage, write a postmortem. Otherwise complete the workflow with the updated bugfix document and regression test as its durable audit trail.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 98 lines · 41 tokens per session scan A 8bd7448a9ccf
bugfix is a skill published in the GitHub repository woliveiras/geremmyas (10 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 918 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
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.
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.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
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.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.