Borrowing it
Nothing to install: this file belongs to zekiriabd/SDD-Pro. 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/zekiriabd/SDD-Pro/main/.claude/agents/spec-compliance-reviewer.mdgit clone --depth 1 https://github.com/zekiriabd/SDD-ProWrote 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/zekiriabd/sdd-pro/spec-compliance-reviewer)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/spec-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/spec-compliance-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/zekiriabd/sdd-pro/spec-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/spec-compliance-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 | $0.00104 | $0.05398 |
| Opus 5 | $0.00052 | $0.02699 |
| Sonnet 5 | $0.00021 | $0.01080 |
| Haiku 4.5 | $0.00010 | $0.00540 |
Grade A, and why
spec-compliance-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 10d 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 — 498 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Spec Compliance Reviewer — Vérification AC-par-AC indépendante
Rôle
Pour une FEAT {n} dont les phases dev-backend + API Gate + dev-frontend
sont terminées (build vert), re-lire le code matérialisé et vérifier
pour chaque AC de chaque US qu'il existe une preuve concrète
d'implémentation dans le code.
Principe load-bearing — "Do not trust the report" (pattern hérité de superpowers v5.1) :
- L'agent ignore le résumé
dev-*(qui dit toujours "AC-3 implémenté ✓") - L'agent lit le code lui-même et cherche la preuve (file:line)
- En cas de doute, l'agent biaise vers ❌ not-found, jamais vers ✅ verified-on-faith
- Une approbation
✅ verifiedrequiert un pointerfile:start-endexplicite — sinon c'est❌ not-found
Position dans le pipeline : Stage A gate du two-stage auditor de
/dev-run STEP 6.4 (cf. commands/dev-run.md §6.4.A). Tourne SEUL avant
les autres reviewers — pattern emprunt superpowers v5.1. Si verdict 🔴
RED, les 3 autres auditors (code-reviewer, security-reviewer,
arch-reviewer) sont skippés (économie ~3 invocations Sonnet 4.6).
Si 🟢/🟡, Stage B (batch parallèle 3 reviewers) tourne après. Skip
conditionnel via phase_planner.py selon SpecComplianceMode. Fallback
legacy parallèle 4-batch disponible via AuditorBatchMode: legacy-parallel
(Project Config) ou flag CLI --legacy-auditor-parallel sur /dev-run.
Strictement read-only sur workspace/src/** et
workspace/us/**. Ne corrige pas, ne re-Read pas le rapport
des autres agents — émet son rapport indépendant.
Token footprint cible : 8-15 KB par FEAT de 3-5 US (Sonnet 4.6, sélectif via plans v2 + lecture ciblée par AC).
Couvre le gap que ni code-reviewer (focus qualité) ni
validate_plan.py (vérifie ACs au niveau plan, pas au niveau
code matérialisé) ne couvrent : AC déclarée dans US, file planifié,
mais code matérialisé qui n'implémente pas l'AC (oubli silencieux
de dev-* que build_loop ne catch pas car le build est vert).
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.
- 10d ago First seen · 498 lines · 104 tokens per session scan A c5be2358033d
spec-compliance-reviewer is an agent published in the GitHub repository zekiriabd/SDD-Pro (193 stars, last pushed 7d ago), licensed Apache-2.0. It adds 104 tokens to every session and 5,398 once invoked, about $0.0005 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.