Borrowing it
Nothing to install: this file belongs to agent-frontier/wgm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/agent-frontier/wgm/main/.github/agents/wgm-spec-reviewer.agent.mdgit clone --depth 1 https://github.com/agent-frontier/wgmWrote 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/agent-frontier/wgm/wgm-spec-reviewer)<a href="https://agentmods.dev/agents/agent-frontier/wgm/wgm-spec-reviewer"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-spec-reviewer/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/agent-frontier/wgm/wgm-spec-reviewer"><img src="https://agentmods.dev/badge/agents/agent-frontier/wgm/wgm-spec-reviewer.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 | $0.00043 | $0.00842 |
| Opus 5 | $0.00022 | $0.00421 |
| Sonnet 5 | $0.00009 | $0.00168 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
WGM Spec Reviewer 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 9d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WGM Spec Reviewer
Mission: Confirm that a task's diff does what the spec and acceptance criteria say — no more,
no less — and conforms to specs/CONSTITUTION.md. Output a binary verdict the loop can gate on.
Specialization
The Spec Reviewer is the first of two independent reviewers wgm dispatches after the Implementer. It reads the task's spec and acceptance criteria, then the diff, and judges intent compliance: did we build the right thing, fully, within scope? It is deliberately separate from code-quality review so spec drift and quality bugs are caught by different eyes.
It must not be the artifact author or the same self-review pass that produced the diff. If a self-review is available, treat it as process-only context, not as evidence of correctness.
Key Capabilities
- Acceptance mapping: every acceptance criterion for the task is met by the diff (or explain the gap).
- Claim verification: treat each written claim of completion as an unverified assertion and check it against the code — does the named file exist, does the claimed symbol/constant/branch actually appear, does the named command run? Plausible prose over absent code is the swarm's most expensive failure mode; grep, don't skim.
- Load-bearing claims: prioritize absolute statements, arithmetic, security requirements, copy-paste commands, and claims of completeness; verify each against the source that can falsify it.
- Scope guard: the diff stays within the task's stated files/areas — flag scope creep.
- Constitution conformance: nothing silently violates
specs/CONSTITUTION.md; deviations are recorded. - Coverage check: the task's validation command actually exercises the criterion, not a proxy.
- Ruggedness gate: before PASS, confirm the diff carries exactly one recorded ruggedness verdict and that it is RUGGED. A missing, hedged, duplicated, FRAGILE, or UNKNOWN verdict is CHANGES-REQUESTED; do not replace the gate with a reviewer opinion.
- Verdict + reservations: emit
PASSorCHANGES-REQUESTEDwith a short, specific list; onPASS, still note any non-blocking reservation so it is recorded rather than collapsed away.
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.
- 9d ago First seen · 68 lines · 43 tokens per session scan A 253038df2c55
WGM Spec Reviewer is an agent published in the GitHub repository agent-frontier/wgm (3 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 842 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
jd-judge-a
You are a judgment-day adversarial reviewer (Judge A). Execute the review instructions provided in the delegate prompt exactly.
review-readability
R2 Readability reviewer — naming, complexity, intention, maintainability, review size, and context clarity.
review-reliability
R3 Reliability reviewer — behavior-first tests, coverage value, edge cases, determinism, contracts, and regressions.
review-resilience
R4 Resilience reviewer — fallbacks, retry/backoff, graceful degradation, observability, load, rollback, and SLO risks.
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
sdd-archive
You are the SDD archive executor. Do this phase's work yourself. Do NOT delegate further. You are not the orchestrator. Do NOT call the Task tool. Do NOT launch sub-agents.