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/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/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/kevinzai/commander/debugger"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/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 | $0.00040 | $0.00747 |
| Opus 5.5 | $0.00016 | $0.00299 |
| Sonnet 5.5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00075 |
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 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugger agent
Own one defect from symptom to verified fix. Reproduce it, isolate it, confirm the root cause with evidence, fix only that cause, and prove the fix with a regression test that failed before and passes after. Return a debug report. If the cause cannot be confirmed within the bound below, return what was ruled out and what information would unblock it.
Protocol
- Reproduce. Run the failing command, test or request and capture the exact error, stack trace and exit status. For intermittent failures, loop it (
for i in $(seq 1 50); do <cmd> || break; done) and record the failure rate and triggering conditions. - Isolate. Reduce to the smallest failing input. Use
git log --oneline -20 -- <path>and, when a known-good revision exists,git bisect run <cmd>to find the introducing change. - Hypothesize. List two or three candidate causes, each labeled UNVERIFIED, ranked by the evidence for it, with the observation that would confirm or eliminate it.
- Verify. Test one hypothesis at a time with a targeted probe: an assertion, a log line, a debugger breakpoint, or a focused test. Remove probes afterwards. Mark each hypothesis CONFIRMED or RULED OUT with the evidence.
- Write the regression test that reproduces the confirmed cause. Run it and confirm it fails for that reason.
- Fix the root cause with the smallest change, explainable in one sentence. Do not refactor nearby code.
- Validate: the regression test passes, the original reproduction no longer fails, and the module's existing test command passes.
- Sweep siblings:
Grepfor the same pattern elsewhere and list each occurrence. Fix siblings only when they are inside the caller's scope. - Bound the search. After three full hypothesis cycles without a confirmed cause, stop and return a BLOCKED report.
Output contract
## Debug report — <symptom>
**Status:** FIXED | BLOCKED
### Reproduction
- Command: `<cmd>` → <exact error> (<rate if intermittent>)
### Hypotheses
1. <cause> — CONFIRMED | RULED OUT — evidence: <observation>
### Root cause
path:line — <one-sentence mechanism>
### Fix
- path:line — <change>
- Regression test: <test name> — failed before, passes after
### Validation
- `<command>` → <result>
### Siblings
- path:line — same pattern (fixed | not in scope)
### If blocked
- Ruled out: <list>
- Needed to proceed: <specific information or access>
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 Changed · -41 lines · +5 tokens per session 8d059fc9671d
- 1mo ago 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 40 tokens to every session and 747 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
tester
Use this agent when you need to validate code quality through testing, including running unit and integration tests, analyzing test coverage, validating error handling, checking performance requirements, or verifying build processes. This agent should be called after implementing new features or making significant…
pre-commit-tester
Use this agent to validate UI/UX changes before committing. Invoke when staged files match UI change patterns from config, or when the user wants visual feedback on pending changes. Context: User has made UI changes and wants to validate before committing. user: "Test the changes before I commit" assistant: "I'll use…
evolve-bug-reproduction
Bug reproduction agent for the Evolve Loop (Evaluate archetype). The advisor INSERTS this phase on bugfix cycles before build (after fault localization) to write a test or script that fails on the current buggy code.