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/coco-research/coco/gsd-debuggergit clone --depth 1 https://github.com/coco-research/cocoWrote 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/coco-research/coco/gsd-debugger)<a href="https://agentmods.dev/agents/coco-research/coco/gsd-debugger"><img src="https://agentmods.dev/badge/agents/coco-research/coco/gsd-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 5.1 | $0.00029 | $0.09943 |
| Opus 5 | $0.00015 | $0.04972 |
| Sonnet 5 | $0.00006 | $0.01989 |
| Haiku 4.5 | $0.00003 | $0.00994 |
Grade A, and why
gsd-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 2d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 2d ago First seen · 1,382 lines · 29 tokens per session scan A 3c83aa377123
gsd-debugger is an agent published in the GitHub repository coco-research/coco (218 stars, last pushed yesterday), with no licence file. It adds 29 tokens to every session and 9,943 once invoked, about $0.0001 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
rig-debugger
Systematic root-cause debugger. Use when investigating a failing test, a production bug, a flaky behavior, or any "this doesn't work and I don't know why" situation. Walks Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix) and refuses to propose fixes before evidence is in.
Env Validator
Audit Python environment consistency across .python-version, uv.lock, pyproject.toml, and CI matrix — flag compatibility drift and suggest remediation.
repair-flow
Diagnose and repair CI/CD failures from logs and pipeline evidence.
debugger
Reproduce un fallo reportado, aísla su causa raíz y propone la corrección mínima. Úsalo cuando haya una prueba fallida, un error o un reporte de bug que diagnosticar. Corrige solo la causa; no refactoriza más allá de eso.
oracle
Highest-reasoning tier, read-only. Use for (a) REVIEW of critical diffs — security, auth, payments, data migrations, public API contracts; (b) SOLVE — designing novel algorithms or root-causing bugs that survived two fix attempts. Expensive — invoke deliberately, with a complete dossier.
auditor.template
WHAT THIS IS: the AUDITOR agent archetype — sweeps for duplication / orphans / dead code. Its findings are UNTRUSTED until grep-confirmed live. It embeds the audit-agent contract so a "duplication" finding can't cause a wrong move (dead code gets deleted, not extracted).