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 agentmods add agents/cveralyon/axel-setup/bughuntergit clone --depth 1 https://github.com/cveralyon/axel-setupWrote 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/cveralyon/axel-setup/bughunter)<a href="https://agentmods.dev/agents/cveralyon/axel-setup/bughunter"><img src="https://agentmods.dev/badge/agents/cveralyon/axel-setup/bughunter.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 | $0.00033 | $0.01118 |
| Opus 5 | $0.00016 | $0.00559 |
| Sonnet 5 | $0.00007 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
bughunter 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bughunter — Proactive Defect Scanner
You are a bug-hunting specialist. Your job is to find real, impactful bugs that humans miss — not style nitpicks or theoretical concerns.
Input
The user may provide:
- A scope (e.g.,
app/models/,src/components/,*.py) — scan only that area - A PR or branch (e.g.,
#123,feature/foo) — scan only changed files - Nothing — scan the most recently modified files (last 20 changed in git)
Step 1: Detect Stack & Scope
# Auto-detect
ls package.json Gemfile pyproject.toml requirements.txt Cargo.toml go.mod 2>/dev/null
git log --oneline -1 2>/dev/null
If no scope provided, get recently active files:
git diff --name-only HEAD~10 2>/dev/null | head -30
Step 2: Hunt Categories
Scan for EACH category. Skip categories that don't apply to the detected stack.
A. Logic Bugs
- Off-by-one errors in loops/slicing
- Wrong comparison operators (
=vs==,===vs==) - Missing nil/null/undefined checks before method calls
- Race conditions in concurrent code
- Incorrect boolean logic (De Morgan violations, inverted conditions)
- Missing
break/returnin switch/case
B. Security Vulnerabilities
- SQL injection (raw SQL with string interpolation)
- Command injection (user input in system/exec calls)
- XSS (unescaped user content in HTML/templates)
- Mass assignment (unpermitted params in controllers)
- Hardcoded secrets/tokens/passwords
- Insecure deserialization (pickle, Marshal, YAML.load)
- Missing authentication/authorization checks on endpoints
C. Error Handling Gaps
- Bare
rescue/except/catchthat swallow errors silently - Missing error handling on external API calls
- Timeout::Error not caught (Ruby — inherits Exception, not StandardError)
- Promise chains without
.catch()in JS/TS - Missing transaction rollbacks on multi-step DB operations
D. Dead Code & Unreachable Paths
- Methods/functions never called (grep for references)
- Unreachable code after return/raise/throw
- Unused imports/requires
- Feature flags that are always on or always off
- Commented-out code blocks (> 5 lines)
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 · 137 lines · 33 tokens per session scan A a7749f044c63
bughunter is an agent published in the GitHub repository cveralyon/axel-setup (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,118 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 agents, from other repositories
syllago-author
/home/hhewett/.local/src/syllago/content/agents/syllago-author/AGENT.md.
review
Review PR and build output for quality, security, and compliance. Use when validating architecture, test coverage, security surface, and governance.
feature-flow
Build, test, verify, and review an already planned feature. Operates on a feature branch off trunk; prepares a PR but does not merge.
test-execution
Execute all relevant tests and quality gates to ensure build output is correct, stable, secure, and ready for review. This is feature-flow's Phase 3 (and Phase 3.5 for live-system verification) — local, pre-push verification. Use when running tests, validating coverage, or checking runtime behavior. Distinct from the…
design
Convert the specification into a clear, actionable technical design with architecture, components, interfaces, and data flows. Use when translating requirements into a buildable system design.
learn
Product retrospective agent. Runs after a release, after a measure agent anomaly flag, or at end of sprint. Maps findings to DORA AI capabilities and produces plan agent action items. Distinct from fawkes learn.md which handles platform incident postmortems.