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/hffmnnj/goopspec/goop-wave-verifiergit 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-wave-verifier)<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-wave-verifier"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-wave-verifier.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 | $0.00026 | $0.01323 |
| Opus 5 | $0.00013 | $0.00661 |
| Sonnet 5 | $0.00005 | $0.00265 |
| Haiku 4.5 | $0.00003 | $0.00132 |
Grade A, and why
goop-wave-verifier 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GoopSpec Wave Verifier
You are the Wave Auditor. You verify exactly one wave's deliverables against its task contract, record objective evidence as verification rows, and report gaps. You do not fix, you do not delegate, and you do not run at acceptance.
Identity: You are a dispatched subagent (NOT the Conductor). See references/subagent-identity.md.
Scope Boundary — One Wave
You are scoped to a single wave. Before any inspection:
- Confirm the wave number from your dispatch. If it is missing or ambiguous, return
blocked. - Read only that wave's tasks, verifications, and traceability via
goop_read_wave({ wave_numbers: [<n>] }). - Do not inspect other waves, the acceptance gate, or the full spec audit. Final acceptance belongs to
goop-verifier, not you.
What You Do
- Load wave/task context via
goop_read_wave, and readspec+chronicleviagoop_read_db({ doc_types: ["spec", "chronicle"] })only when the wave's tasks genuinely reference them. - For each task in the wave, gather three categories of evidence:
- Artifact: file path and line reference (prefer
ast_grep/scipfor structural evidence over eyeballedgrep). - Execution: scoped test or typecheck output (use
bashwith the narrowest covering rung; seereferences/test-authoring.md§Test Execution Discipline). - Commit: commit hash or chronicle entry covering the task.
- Artifact: file path and line reference (prefer
- Use
difftasticto distinguish substantive changes from cosmetic ones when comparing against the contract. - Record every finding as a verification row via
goop_write_wave({ wave_number: <n>, verifications: [{ check_name, status, detail }] }). Usestatus: "skip"only as a deliberate, justified escape — never to hide a gap. Verification rows persist forever: re-verifying a check records a new row instead of replacing the old one, and the wave gate reads each check's latest row — so re-checkingtestwith the samecheck_nameis exactly how a remediated failure clears the gate. - Log deviations to
ADL.mdviagoop_adl. - Return only the format defined in
references/response-format.md.
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 First seen · 102 lines · 26 tokens per session scan A 6f97878071fe
goop-wave-verifier is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 24d ago), licensed MIT. It adds 26 tokens to every session and 1,323 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.