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 cmdr-chara/codex-toolkit --skill bug-findergit clone --depth 1 https://github.com/cmdr-chara/codex-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/cmdr-chara/codex-toolkit/bug-finder)<a href="https://agentmods.dev/skills/cmdr-chara/codex-toolkit/bug-finder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/bug-finder/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/cmdr-chara/codex-toolkit/bug-finder"><img src="https://agentmods.dev/badge/skills/cmdr-chara/codex-toolkit/bug-finder.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 | $0.00032 | $0.00617 |
| Opus 5.5 | $0.00013 | $0.00247 |
| Sonnet 5.5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
bug-finder 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 24d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Finder
Search for unknown correctness defects without turning suspicious code into unsupported bug claims.
Trigger boundary
Use this skill for:
- proactive bug hunts without a known failing symptom;
- searches for races, lifecycle failures, data-loss paths, duplicate effects, stuck ownership, or broken recovery;
- requests to distinguish confirmed defects from plausible theories.
Do not trigger for:
- a concrete failure whose cause is unknown; use
debugging-investigator; - a defined PR/diff review; use
review-and-refactor-code; - security-only review; use
security-review; - generic improvement prioritization or release approval.
Required inputs
Resolve repository/candidate identity, hunt scope, architecture boundaries when needed, available contracts/tests/fixtures/traces, safe experiment permissions, and protected user work.
Safety baseline
- Preserve the working tree and uncommitted work.
- Start read-only and do not mutate production data or external systems to prove a theory.
- Generated/vendor code is evidence only until its authoritative source is known.
- Missing tests, odd code, or severity intuition are not proof of a defect.
Workflow
- Define the hunt. State in-scope subsystems, excluded surfaces, and coverage limits.
- Derive invariants. Write observable rules that must hold: exactly-once/at-most-once events, ownership release, persistence durability, idempotency, ordering, retry bounds, cleanup, or state-transition rules.
- Prioritize surfaces. Favor stateful boundaries, concurrency, recovery, persistence, cancellation, caching, serialization, and cross-process ownership.
- Create candidates. Record each candidate in
references/candidate-ledger.mdwith invariant, evidence, falsifier, and status. - Prove or retire. Use the smallest safe fixture, trace, targeted test, or static contract evidence that can discriminate the claim. A confirmed bug requires an observable contract violation.
- Rank confirmed defects. Separate confirmed, plausible, and retired candidates. State unexamined high-risk surfaces rather than implying exhaustive coverage.
- Hand off. If causal explanation or the smallest fix remains uncertain, pass the confirmed symptom to
debugging-investigator.
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.
- 24d ago Changed · -201 lines · -65 tokens per session d773d309b5ca
- 1mo ago First seen · 256 lines · 97 tokens per session scan A ec652ea33408
bug-finder is a skill published in the GitHub repository cmdr-chara/codex-toolkit (2 stars, last pushed 11d ago), licensed MIT. It adds 32 tokens to every session and 617 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 2026-08-31.
Other skills, from other repositories
trace
Use when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports. Systematic root-cause analysis before any patch — never blind-patches symptoms. Standalone, ends with a final-integration review of the fix. Trigger with /hyperflow:trace, "debug this", "find the root cause", "why…
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
code-coherence-review
Reviews code and plans for logic coherence, correctness, and structural integrity.