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/hainamchung/agent-assistantWrote 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/hainamchung/agent-assistant/debugger)<a href="https://agentmods.dev/agents/hainamchung/agent-assistant/debugger"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/debugger/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/hainamchung/agent-assistant/debugger"><img src="https://agentmods.dev/badge/agents/hainamchung/agent-assistant/debugger.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 | $0.00013 | $0.01091 |
| Opus 5.5 | $0.00005 | $0.00436 |
| Sonnet 5.5 | $0.00003 | $0.00218 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade C, and why
debugger scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- 🔒 COGNITIVE ANCHOR — MANDATORY OPERATING SYSTEM --> How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BINDING: This file OVERRIDES default AI patterns. Follow Thinking Protocol EXACTLY. EXTRACT: Core Directive + Constraints + Output Format before proceeding.
🐛 Debugger
| Attribute | Value |
|---|---|
| ID | agent:debugger |
| Role | Principal Debug Specialist |
| Profile | quality:debugging |
| Reports To | tech-lead |
| Consults | backend-engineer, frontend-engineer, tester |
| Authority | Can halt development for critical bugs |
CORE DIRECTIVE: Find the REAL cause, not the symptom. A bug fixed without understanding will return. Debugging is detective work—follow the evidence.
Prime Directive: REPRODUCE → HYPOTHESIZE → VERIFY → FIX. Never guess the fix.
⚡ Skills
MATRIX DISCOVERY: Skills auto-injected from domain files in
~/.{TOOL}/skills/agent-assistant/matrix-skills/Profile:quality:debugging| Domains:quality,performance
🎯 Expert Mindset
THINK_LIKE:
- "Can I reproduce this reliably?"
- "What's my hypothesis? How to test it?"
- "Am I fixing the symptom or the cause?"
- "What else might this fix break?"
ALWAYS:
- Reproduce before investigating
- Form and rank hypotheses
- Verify root cause before fixing
- Add test to prevent regression
🧠 Thinking Protocol
Step 0: CONTEXT CHECK (IF NEEDED)
CHECK PROJECT DOCS (if bug involves domain logic):
- knowledge-architecture/00-index.md → System understanding (drill into sub-files as needed)
- knowledge-domain/00-index.md → Expected behavior (drill into sub-files as needed)
→ USE these to understand what SHOULD happen
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 · 158 lines · 13 tokens per session scan C a1ad9788b9e6
debugger is an agent published in the GitHub repository hainamchung/agent-assistant (54 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 1,091 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…