Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add robzilla1738/roberts-skills/plugin install bughunt-suiteWrote 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/commands/robzilla1738/roberts-skills/bughunt)<a href="https://agentmods.dev/commands/robzilla1738/roberts-skills/bughunt"><img src="https://agentmods.dev/badge/commands/robzilla1738/roberts-skills/bughunt.svg" alt="Measured on agentmods" 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 | $0.00682 |
| Opus 5 | $0.00016 | $0.00341 |
| Sonnet 5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
bughunt 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.
What it actually says
Run a bug hunt against: $ARGUMENTS
Load and follow the bughunt skill at ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/SKILL.md exactly. Parse $ARGUMENTS for:
- Scope —
diff(vs the merge base) ·staged(git-staged changes) · a path likesrc/api· a named module · empty = whole repo. - Depth —
quick(a handful of cells, fast) ·deep(full fan-out; the default for a whole-repo hunt). ci— non-interactive mode: don't ask the user anything, run merge with--require-verified --require-coverage --strict --fail-on critical-high, and surface the exit code (0 no new Critical/High / 1 new Critical/High / 3 malformed or IO error). Use--fail-on anyonly when Medium/Low should return 2.
Then run the loop:
- Recon & pre-pass — detect platform and map trust boundaries. When
python3is available, run the deterministic pre-pass for ranked targets:python3 ${CLAUDE_PLUGIN_ROOT}/skills/bughunt/scripts/bughunt.py census,hotspots,signals,deps(see tooling.md). On a large/unfamiliar repo, confirm scope first (skip the prompt underci). - Fan out — build the (lens × hotspot) grid and dispatch hunters via the capability ladder in orchestration.md: the shipped Workflow script if available, else parallel Tasks, else a sequential walk. Hunters return findings as JSON.
- Verify (mandatory) — a skeptic pass tries to refute every candidate before it reaches the report (verification.md).
- Merge & triage — pipe findings through
bughunt.py merge(fingerprint, dedupe, cross-validate, suppress, baseline-diff) and score with the triage rubrics. Underci, include--require-verified --require-coverage --strict --fail-on critical-high. - Report —
bughunt.py renderemits the ranked markdown (+ HTML + SARIF) into.bughunt/.
This is report-only: surface and prove bugs, do not edit code unless I ask. If python3 is unavailable, follow the markdown fallback (no scripts; findings stay in markdown). If $ARGUMENTS is empty, ask what to hunt (whole repo, a module, or a diff) and which depth.
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 First seen · 23 lines · 32 tokens per session scan A d3c82e630e07
bughunt is a command published in the GitHub repository robzilla1738/roberts-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 682 once invoked, about $0.0002 per session on Opus 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 commands, from other repositories
maintainer-review-error-handling
Review the PR for error-handling correctness — surfaced errors, no silent swallows, consistent error patterns (Pi-tuned).
refactor-clean
Remove dead code, duplicates, and tech debt with safe automated cleanup.
refactor-clean
Safely identify and remove dead code with test verification.
refactor-clean
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
modify
Command "modify" from MartyBonacci/specswarm, covering user input, flag parsing, parse flags from arguments, mode routing and goal.
harness:audit
Cross-dimensional codebase audit orchestrator — classify repo shape, fan out parallel read-only audit agents, dedup and severity-rank findings against existing issues, publish grouped tracking issues.