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/ant4g0nist/ChiefWiggumWrote 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/ant4g0nist/chiefwiggum/hunt-help)<a href="https://agentmods.dev/commands/ant4g0nist/chiefwiggum/hunt-help"><img src="https://agentmods.dev/badge/commands/ant4g0nist/chiefwiggum/hunt-help/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/commands/ant4g0nist/chiefwiggum/hunt-help"><img src="https://agentmods.dev/badge/commands/ant4g0nist/chiefwiggum/hunt-help.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 | $0.00009 | $0.00882 |
| Opus 5 | $0.00005 | $0.00441 |
| Sonnet 5 | $0.00002 | $0.00176 |
| Haiku 4.5 | $0.00001 | $0.00088 |
Grade A, and why
hunt-help 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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief Wiggum Vulnerability Hunter - Help
Quick Start
/vuln-hunt --profile <path-to-profile.yaml> --target <path-to-codebase> --max-iterations 50
Commands
| Command | Description |
|---|---|
/chief-wiggum:vuln-hunt |
Start a new vulnerability hunt |
/chief-wiggum:hunt-status |
Show current hunt progress and stats |
/chief-wiggum:resume-hunt |
Continue an interrupted hunt (works even after completion!) |
/chief-wiggum:review-hunt |
Review findings, candidates, and results |
/chief-wiggum:restore-hunt |
Restore a previously archived hunt |
/chief-wiggum:cancel-hunt |
Stop the current hunt (preserves data) |
/chief-wiggum:hunt-help |
Show this help message |
How It Works
Chief Wiggum is a Ralph Wiggum-style iterative loop with four phases:
Phase 0: CONTEXT-BUILD (First Iteration)
- Analyze the target codebase structure
- Map attack surface, entry points, trust boundaries
- Create a Hunt Plan (hunt-plan.json) that guides exploration
- Signal:
<transition>EXPLORE</transition>
Phase 1: EXPLORE (Uses Hunt Plan)
- Agent picks highest-priority unexplored area from Hunt Plan
- Search for vulnerability patterns using Glob, Grep, Read
- Create candidate files when something looks interesting
- Update Hunt Plan progress
- Signal:
<transition>DEEP-DIVE:candidates/XXX.md</transition>
Phase 2: DEEP-DIVE
- Validate candidates with guided questions
- Read actual source code and provide evidence
- Confirm → SCRUTINIZE, Reject → back to EXPLORE
Phase 3: SCRUTINIZE
- Final verification, try to disprove
- Generate PoC and vulnerability report
- Signal:
<promise>VULNERABILITY_CONFIRMED</promise>
Completion Signals
| Signal | Meaning |
|---|---|
<promise>VULNERABILITY_CONFIRMED</promise> |
Found and confirmed a vulnerability! |
<promise>HUNT_EXHAUSTED</promise> |
Explored all scope areas, no findings |
Profile Format
name: "My Hunt"
description: "What you're looking for..."
language: "cpp"
scope:
include_paths: ["src/**/*"]
exclude_paths: ["tests/**/*"]
focus_keywords: ["dangerous_pattern"]
constraints:
- "REJECT: False positive pattern"
- "REQUIRE: Must be exploitable"
checklist:
- "Is input validated?"
- "Are bounds checked?"
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.
- 10d ago First seen · 99 lines · 9 tokens per session scan A dd23daf5e478
hunt-help is a command published in the GitHub repository ant4g0nist/ChiefWiggum (10 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 882 once invoked, about $0.0000 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.