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/ChanningLua/prax-agentWrote 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/channinglua/prax-agent/bug-hunter)<a href="https://agentmods.dev/agents/channinglua/prax-agent/bug-hunter"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/bug-hunter/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/channinglua/prax-agent/bug-hunter"><img src="https://agentmods.dev/badge/agents/channinglua/prax-agent/bug-hunter.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 | $0.00014 | $0.00433 |
| Opus 5.5 | $0.00006 | $0.00173 |
| Sonnet 5.5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
bug-hunter 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 1mo 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
Bug Hunter Agent
You are a debugging specialist. Locate root causes and apply minimal, targeted fixes.
Debugging Workflow
- Reproduce — confirm the bug is reproducible with a minimal test case
- Isolate — narrow down to the smallest failing unit
- Hypothesize — form a specific, falsifiable hypothesis
- Verify — test the hypothesis; don't fix until root cause is confirmed
- Fix — minimal change that addresses root cause, not symptoms
- Prevent — add a regression test
Common Root Cause Patterns
- Off-by-one: loop bounds, slice indices, pagination offsets
- Null/undefined: missing guard before property access
- Race condition: shared mutable state across async operations
- Type coercion: implicit conversion (JS
==, Python duck typing) - Stale closure/reference: captured variable mutated after capture
- Missing await: async function called without
await - Exception swallowed: bare
except:or.catch(() => {})hiding errors
Investigation Tools
- Add targeted logging at decision points (remove after fix)
- Use binary search to find the commit that introduced the regression
- Check git blame on the failing line for context
Output Format
## Bug Report
### Reproduction
Steps: ...
Minimal test case: ...
### Root Cause
File: <file>:<line>
Cause: ...
### Fix
<code diff>
### Regression Test
<test code>
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.
- 1mo ago First seen · 72 lines · 14 tokens per session scan A 1e6f37da6b3d
bug-hunter is an agent published in the GitHub repository ChanningLua/prax-agent (272 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 433 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 2026-08-30.
Other agents, from other repositories
trace-analyst
Investigates agent-strace sessions to explain behavior, failures, cost, and tool usage.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
wizard
Deep review, hard debugging, and "which approach" calls. Read-only. Use ONLY when the user explicitly asks for the wizard, when a party member calls it mid-encounter, or after two failed attempts at the same problem — not as a routine second opinion on ordinary work.