Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bluebear-io/angry-bearnpx agentmods add skills/bluebear-io/angry-bear/bug-fixWrote 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/bluebear-io/angry-bear/bug-fix)<a href="https://agentmods.dev/skills/bluebear-io/angry-bear/bug-fix"><img src="https://agentmods.dev/badge/skills/bluebear-io/angry-bear/bug-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/bluebear-io/angry-bear/bug-fix"><img src="https://agentmods.dev/badge/skills/bluebear-io/angry-bear/bug-fix.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 | $0.00061 | $0.00706 |
| Opus 5.5 | $0.00024 | $0.00282 |
| Sonnet 5.5 | $0.00012 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
bug-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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix — Mandatory Sequence
Copy this checklist and check off items as you complete them. Do NOT skip or reorder steps.
Bug Fix Progress:
- [ ] Step 1: Write failing test (real filesystem, real execution, NO mocks)
- [ ] Step 2: Run test, confirm it FAILS
- [ ] Step 3: Show user the failing output
- [ ] Step 4: Write minimal fix
- [ ] Step 5: Run regression test, confirm it PASSES
- [ ] Step 6: Run full test suite + lint, confirm no regressions
- [ ] Step 7: Report summary
Step 1: Write a failing test
Read 1-2 files to locate the bug entry point. Then IMMEDIATELY write a test.
Tests must exercise real code paths:
- CLI commands: use
cobra.Commandwith captured stdout/stderr - Engine logic: call the real function with real inputs
- State management: use
t.TempDir()with real file I/O - TUI: use
tea.KeyMsgto simulate user input, verify model state - Adapters: use real JSON input, verify parsed output
Do NOT use mocks. This project has zero mock dependencies. Tests use real filesystems, real JSON parsing, real enforcement logic.
Test naming: TestBugFix_DescriptionOfBug
Test location: same _test.go file as the code being fixed
If you cannot reproduce in a test after 5 minutes, STOP and ask the user for a detailed scenario.
Step 2: Run test, confirm FAIL
go test -run TestBugFix_DescriptionOfBug ./internal/...
If the test passes, it does not reproduce the bug. Rewrite it.
Step 3: Show failing output
Print the test failure to the user. Do NOT proceed to fixing until the user sees the reproduction.
Step 4: Minimal fix
Change only what is necessary. No refactoring, no cleanup, no unrelated improvements.
Step 5: Run regression test
go test -run TestBugFix_DescriptionOfBug ./internal/...
Must pass.
Step 6: Full test suite + lint
make lint test
All tests must pass. Coverage must not drop below 80%.
Step 7: Report
- Root cause (1 sentence)
- Test added (file path + test name)
- Code changed (file path + what changed)
- Results (regression passes, full suite passes, lint clean)
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.
- 1mo ago First seen · 85 lines · 61 tokens per session scan A 533630515e0b
bug-fix is a skill published in the GitHub repository bluebear-io/angry-bear (17 stars, last pushed 26d ago), licensed MIT. It adds 61 tokens to every session and 706 once invoked, about $0.0002 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.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
genotoxic
Graph-informed mutation testing triage. Parses codebases with Trailmark, runs mutation testing and necessist, then uses survived mutants, unnecessary test statements, and call graph data to identify false positives, missing test coverage, and fuzzing targets. Use when triaging survived mutants, analyzing mutation…
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.