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 escapeboy/ai-prompts --skill fix-buggit clone --depth 1 https://github.com/escapeboy/ai-promptsWrote 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/escapeboy/ai-prompts/fix-bug)<a href="https://agentmods.dev/skills/escapeboy/ai-prompts/fix-bug"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/fix-bug/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/escapeboy/ai-prompts/fix-bug"><img src="https://agentmods.dev/badge/skills/escapeboy/ai-prompts/fix-bug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00030 | $0.00818 |
| Opus 5.5 | $0.00012 | $0.00327 |
| Sonnet 5.5 | $0.00006 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
fix-bug 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 27d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix-bug
Three-phase bug fix that finds ALL occurrences, fixes atomically, and validates with a regression test.
When to Use (and When NOT to)
| Use this skill for | Use a simpler approach for |
|---|---|
| A bug that could touch multiple files (renamed prop, broken route, changed model attribute) | A one-line fix with no cross-file symbol — just fix it directly |
| The "#1 friction source": partial fixes that miss a reference elsewhere | You already know the single file/line to change and nothing else references it |
| A bug you want validated with a dedicated regression test | A trivial typo/copy fix that doesn't warrant its own test |
Phase 1 — Comprehensive Investigation
Before touching any code:
- Reproduce the issue and capture the exact error message / stack trace
- Identify the primary symbol involved (function name, route, variable, class, column)
- Grep the entire codebase for every reference to that symbol:
- Controllers, services, models
- View templates (Blade / JSX / ERB / Twig — server-rendered views are the most-missed spot)
- Tests (feature + unit)
- Route definitions (all route files, not just the obvious one)
- Config files
- JS/CSS files if relevant
- Document: full list of files that reference the broken symbol
- Check for the same bug pattern in similar locations (e.g. if one route is broken, check all routes of the same type)
Do not proceed until you have the complete reference map.
Phase 2 — Fix with Full Coverage
Apply changes atomically across every file found in Phase 1:
- For renamed variables/properties: update the definition + every view, controller, test, and config
- For broken routes: check all route files, all route-helper calls, all redirects and links
- For removed/changed model attributes: update mass-assignment lists (
$fillableor equivalent), factories, seeders, and all tests that reference those attributes - For middleware changes: check route groups, kernel/middleware registration, and all test middleware overrides
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.
- 27d ago Changed · +21 lines 94556e5f7f23
- 1mo ago First seen · 63 lines · 30 tokens per session scan A 3e48ed70a8a2
fix-bug is a skill published in the GitHub repository escapeboy/ai-prompts (91 stars, last pushed 15d ago), licensed MIT. It adds 30 tokens to every session and 818 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 2026-08-30.
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.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
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.