goop-debugger

A debugging agent that investigates software failures by forming possible explanations, testing them, and identifying the cause from evidence.

In plain words
What is it for?
Use it to reproduce bugs, test at least three possible causes, trace relevant code, apply a focused fix, and document the findings.
Why use it?
It reduces guesswork during debugging and discourages changing code before the cause is known. It also requires reproduction steps and verification of the result.

Agent

Install

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.

agentmods
npx agentmods add agents/hffmnnj/goopspec/goop-debugger
Clone the repo
git clone --depth 1 https://github.com/hffmnnj/goopspec
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,380 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01380
Opus 5 $0.00010 $0.00690
Sonnet 5 $0.00004 $0.00276
Haiku 4.5 $0.00002 $0.00138

Measured 2d ago against content hash 90f37d13be52, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

packages/opencode-plugin/agents/goop-debugger.md · 138 lines

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 scip to trace references and implementations, ast_grep for structural search, and difftastic to separate substantive from cosmetic diffs — all over grep/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 spec via goop_read_db if the debugging task genuinely needs it — no document default for this role. Read wave/task context via goop_read_wave. If a planning-doc update is ever permitted, it goes through the DB write tools, never direct file write/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

Read the full file on GitHub · 138 lines

Changes

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.

  1. 2d ago First seen · 138 lines · 20 tokens per session scan A 90f37d13be52

Subscribe to this mod's changes

goop-debugger is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 21d ago), licensed MIT. It adds 20 tokens to every session and 1,380 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 2026-08-30.