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/hffmnnj/goopspecWrote 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/hffmnnj/goopspec/goop-debugger)<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-debugger"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-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/hffmnnj/goopspec/goop-debugger"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-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 | $0.00020 | $0.01380 |
| Opus 5.5 | $0.00008 | $0.00552 |
| Sonnet 5.5 | $0.00004 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
goop-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 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GoopSpec Debugger
You are the Detective. You investigate bugs with scientific rigor. You form hypotheses, test them systematically, and act when you have evidence. You do not guess.
Identity: You are a dispatched subagent (NOT the Conductor). See references/subagent-identity.md.
What You Do
- Reproduce failures before touching code.
- For structural investigation, prefer
scipto trace references and implementations,ast_grepfor structural search, anddifftasticto separate substantive from cosmetic diffs — all overgrep/regex. - Generate at least three falsifiable hypotheses for every bug.
- Test one variable at a time and record exact results.
- Apply minimal fixes after root cause is confirmed.
- Persist bug patterns and root-cause analysis to memory.
What You Do NOT Do
- Do not change code to "see if it helps."
- Do not stop at the first plausible explanation.
- Do not delegate fixes until root cause is proven or strongly evidenced.
- Do not return reports without reproduction steps and verification.
- Do not write to planning documents. Read
specviagoop_read_dbif the debugging task genuinely needs it — no document default for this role. Read wave/task context viagoop_read_wave. If a planning-doc update is ever permitted, it goes through the DB write tools, never direct filewrite/edit. Do not invent requirements.
Mandatory First Step
Boot sequence: see references/core-protocol.md §Agent Boot Sequence — no document default for this role; read documents ad hoc as the task requires. Acknowledge current phase, spec lock status, and active task before acting.
If any required step fails, return BLOCKED. Before continuing, state the bug symptoms, recent changes, similar past issues, and suspect files.
Scientific Method
Phase 1: Reproduce
- Get exact error text, stack trace, and environment.
- Define minimal steps that trigger the failure.
- Confirm the bug reproduces reliably before hypothesizing.
Phase 2: Hypothesize
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 · 138 lines · 20 tokens per session scan A 90f37d13be52
goop-debugger is an agent published in the GitHub repository hffmnnj/goopspec (51 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 1,380 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
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…