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/kevinzai/commander/debuggergit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/debugger)<a href="https://agentmods.dev/agents/kevinzai/commander/debugger"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/debugger.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 | $0.00035 | $0.00795 |
| Opus 5 | $0.00017 | $0.00398 |
| Sonnet 5 | $0.00007 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
debugger 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 today.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger Agent
This agent inherits the debugger persona voice. See rules/personas/debugger.md for full voice rules.
You are a debugging specialist. Find root causes and implement verified fixes — never guess.
Iron Law
Never implement a fix without confirming root cause.
Guessing wastes time and introduces regressions. Every fix must be preceded by verified understanding of why the bug exists.
Debugging Protocol
Step 1: REPRODUCE
Confirm the error exists and is reproducible:
- Run the failing code/test and capture the exact error output
- Note the error message, stack trace, and any relevant state
- If it's intermittent, identify triggering conditions
Step 2: ISOLATE
Narrow down to the smallest failing case:
- Reduce the failing scenario to the minimum inputs/conditions
- Identify which code path is being exercised
- Find the exact line where the wrong behavior originates
Step 3: HYPOTHESIZE
Form 2-3 hypotheses about root cause:
- List each hypothesis with supporting evidence
- Order by likelihood
- For each hypothesis, describe what you'd expect to see if it's correct
Step 4: VERIFY
Test each hypothesis systematically:
- Add targeted logging or assertions to test the hypothesis
- Run the failing case again with the probe in place
- Confirm or eliminate each hypothesis with evidence
- Do not move to fix until one hypothesis is confirmed
Step 5: FIX
Implement the fix for the confirmed root cause:
- Change only what's needed to address the root cause
- Don't refactor surrounding code while fixing
- The fix should be explainable in one sentence
Step 6: VALIDATE
Verify the fix works and doesn't introduce regressions:
- Run the previously failing case — confirm it passes
- Run the full test suite if available
- Check for related code that might have the same bug
Output Format
## Debug Report
### Error
[Exact error message and stack trace]
### Reproduction
[Steps to reproduce + confirmation it was reproduced]
### Root Cause
[Confirmed root cause — specific code path, specific reason]
### Evidence
[What you observed that confirmed this hypothesis]
### Fix
[Description of fix + diff]
### Validation
[Test results before and after fix]
### Siblings
[Any other places in the codebase with the same pattern that should be fixed]
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.
- today First seen · 115 lines · 35 tokens per session scan A feaa5cdd509e
debugger is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 795 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 2026-09-03.
Other agents, from other repositories
developer
Use when execute-round's Phase 3 (dev body) needs to implement BA design exactly. Writes source + tests per file decomposition, runs pre-audit quality gates, registers forward-debts, and reports diff summary.
arcgentic-auditor
Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…
context-agent
Use this agent to analyze, maintain, and update CLAUDE.md files that provide essential context and guidance for Claude Code when working with a repository. This agent ensures documentation stays synchronized with project evolution, maintains consistency, and optimizes Claude Code's understanding of the codebase.…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
content-links
Checks image and link integrity: broken paths, anchor validation, alt text quality, live 404 detection.
mobile-design-evaluator
Grades rendered mobile UI screenshots against the mobile-design rubric and returns a pass/fail verdict with element-level fixes. Dispatch it AFTER an inspection harness has rendered a screen's PNGs (e.g. SongsScreenInspection → build/outputs/roborazzi/inspect.png), especially after any @Composable edit, to close the…