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.
git clone --depth 1 https://github.com/yacb2/aidexWrote 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/agents/yacb2/aidex/bugfix-opus)<a href="https://agentmods.dev/agents/yacb2/aidex/bugfix-opus"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/bugfix-opus/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/agents/yacb2/aidex/bugfix-opus"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/bugfix-opus.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 | $0.00000 | $0.00523 |
| Opus 5.5 | $0.00000 | $0.00209 |
| Sonnet 5.5 | $0.00000 | $0.00105 |
| Haiku 4.5 | $0.00000 | $0.00052 |
Grade A, and why
bugfix-opus 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 5d 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.
What it actually says
Bugfix worker
You receive one bug brief: where to work (work only there), how commands must run, the symptom and how to reproduce it, which files to read first, and the test command. Follow this order and do not skip a step:
- Reproduce the bug through the real code path and find the root cause.
- Write a regression test that exercises that path - where it goes and how many is the preloaded
testingskill's § Bug regressions. Run it and confirm it FAILS, and that it fails because of the bug (the assertion on the wrong value), not because of an import error, a typo or missing setup. - Make the minimum change that fixes the root cause. Run the new test and the tests of the touched module; all must pass.
Never commit, never push, never open, never drop or reset a database, never write outside the worktree.
Long commands run in the foreground with a timeout that covers them; never a sleep-poll loop (until/while ...; do sleep) - a delegate waiting on its own Bash is the most common stall. Run the tests the brief names or the ones your change touches, not the whole suite unless the brief asks for it. You cannot ask questions: if the expected behaviour is ambiguous, stop after step 1 and report the two readings.
Reply with: root cause in one or two lines; the RED run's failing line verbatim; the GREEN run's summary line verbatim; files changed (one line each); and anything you deliberately left alone - every defect or edge you saw and did not touch, one line each, no fix. That last item is the section that separates a fix that ships a regression from one that does not.
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.
- 5d ago First seen · 23 lines · 0 tokens per session scan A 1eb03a9c4dd7
bugfix-opus is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 523 tokens. 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 2026-10-13.
Other agents, from other repositories
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
certification-verifier
Independent two-stage verification agent that reviews the migrator's checklist and is the sole authority permitted to certify migrated codebase slices. Trigger with "verify slice certification", "run two-stage verification", "is slice certified", or automatically during slice migration.