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 ulises-jeremias/agent-toolkit --skill megalinter-fixgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/ulises-jeremias/agent-toolkit/megalinter-fix)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/megalinter-fix"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/megalinter-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/ulises-jeremias/agent-toolkit/megalinter-fix"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/megalinter-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 | $0.00091 | $0.01532 |
| Opus 5.5 | $0.00036 | $0.00613 |
| Sonnet 5.5 | $0.00018 | $0.00306 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
megalinter-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 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MegaLinter fix
Fix the MegaLinter errors you were given (output contract of megalinter-check: linter keys, error counts, files, sample error lines).
1. Prepare
- If the current branch is the default branch (
main/master), create a branch first:git checkout -b megalinter/fix-<topic>. - Group the errors by linter key. Handle blocking linters (❌) first; mention non-blocking ones (⚠️) to the user but don't fix them unless asked.
2. Load the fix guides — lazily
For each failing linter only, read its fix guide from this skill's directory: linters/<linter_key_lower>.md (e.g. linters/python_ruff.md). The index is in linters/README.md.
Each guide contains a generated block (auto-fix support, config/ignore files, rule documentation URLs, tuning variables, known non-lint failure patterns) and researched fix instructions. Never load guides for linters without errors.
3. Fix
In this order:
- Auto-fixable linters (guide says auto-fix supported): if a container engine is available, run
npx mega-linter-runner --linter <KEY> --fix [failing files...](add--container-engine podmanwhen using podman; usenpx mega-linter-runner@betawhen.mega-linter.ymlpinsMEGALINTER_VERSION: beta— see the version rule inmegalinter-check). Otherwise apply the underlying tool's documented fix behavior manually. If no engine is installed/running, ask the user first, then followcontainer-engine.mdin themegalinter-checkskill directory. - Manual fixes: fix remaining errors file by file following the guide's instructions. Consult the rule documentation URLs when unsure what a rule means.
- Errors not covered by the guide (unknown rule, missing/outdated guide): browse the web — fetch the rule's official documentation (start from the URLs in the guide's generated block) or search for the exact error message — before deciding on a fix. Never guess a fix or a suppression syntax.
- Ambiguous cases (fix would change behavior, several valid approaches, false positive suspected): ask the user, presenting the options — fix this way, inline-disable with justification, or ignore.
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 Changed · +2 lines fa4fb9b67d2e
- 1mo ago First seen · 91 lines · 91 tokens per session scan A 6cc38525a2b8
megalinter-fix is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed 2d ago), licensed MIT. It adds 91 tokens to every session and 1,532 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…
analyze-failures
Triage Katalon True Platform/TestOps test failures and file defects. Use when you need to investigate failed test results, classify each failure as product defect vs automation defect vs environment/data issue, cluster failures by common signature, find likely root cause from execution data, and optionally create…
vibeflow-hotfix
Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Use when a defect was observed and the evidence is in hand — an error message, a failing log, real data misbehaving — wherever…
impact-trace
For a change point (function / type / endpoint / SQL column), enumerate its real blast radius across six dimensions with a grep citation per row, then derive the regression test scope. Every impact-table row must trace to a real search hit — never a self-asserted claim.
debugging-livekit-agents
Drives a multi-turn conversation with a LiveKit agent running locally to see what it does. Use when the user says "test my agent", "try my agent", "does this work", "why did it call that tool", "it says the wrong thing when I ask X", "test this change", or whenever you have edited an agent and need to check how it…
oma-debug
Diagnose a reproducible failure, fix its cause, and verify the regression. Use for crashes, incorrect behavior, and failing tests.