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 commands/hffmnnj/goopspec/goop-quickgit clone --depth 1 https://github.com/hffmnnj/goopspecWhat 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 | $0.00013 | $0.00491 |
| Opus 5 | $0.00006 | $0.00246 |
| Sonnet 5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
goop-quick 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 3d 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.
What it actually says
/goop-quick
Run a small task without a full discovery/spec contract. Use only when the task is truly small and safe.
Load references
goop_reference({ name: "phase-gates" })
goop_reference({ name: "core-protocol" })
Qualify
Quick mode is appropriate when the task is:
- A single file, or at most 3 tightly coupled files.
- Clear, unambiguous intent.
- No architectural decisions.
- Estimated under 30 minutes.
- No new dependencies.
If it does not qualify, switch to /goop-discuss.
Steps
- Capture one-line intent and one success criterion.
- Log the bypass decision to
ADL.mdviagoop_adl. - Delegate to the appropriate executor tier.
- Create an atomic commit.
- Verify the fix.
- Ask the user to confirm completion.
Self-Edit Authority
In /goop-quick mode only, the orchestrator may make trivial edits itself without delegating to a subagent — but only when ALL five conditions hold:
- Single file only — not 2–3 files (stricter than Quick mode's general qualify criteria).
- File lives in
.goopspec/or the project-config root (e.g..goopspec/config.json) — neversrc/,lib/,app/,packages/*/src/,agents/,commands/,skills/. - Under 5 lines changed (added + removed combined).
- No logic/behavior implications — a typo fix, a config value bump, a comment, markdown formatting only.
- Already inside
/goop-quickmode — this is not a substitute for delegation during standard/goop-execute.
If any condition is not met, the orchestrator must delegate to the appropriate executor tier (step 3 below) — no exceptions.
Anti-patterns
- Do NOT use quick mode for ambiguous, architectural, or multi-wave work.
- Skip verification or the ADL log.
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.
- 3d ago First seen · 58 lines · 13 tokens per session scan A d162886b6f6d
goop-quick is a command published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 21d ago), licensed MIT. It adds 13 tokens to every session and 491 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.