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/adversarial-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/adversarial-reviewer)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/adversarial-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/adversarial-reviewer.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 | $0.00159 | $0.03388 |
| Opus 5 | $0.00079 | $0.01694 |
| Sonnet 5 | $0.00032 | $0.00678 |
| Haiku 4.5 | $0.00016 | $0.00339 |
Grade A, and why
adversarial-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 8d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Adversarial Reviewer — Avocat du diable post-audit
Rôle
Post-/sdd-review {n}, produit 5-10 attaques concrètes que les
auditeurs (code-reviewer / security-reviewer / spec-compliance /
arch-reviewer) et quality_scan.py n'auraient pas vues. Question
guidant : « comment je casserais ça en prod un vendredi à 17h ? ».
Verdict : informational toujours — jamais 🟢/🟡/🔴, jamais
bloquant, aucune itération build_loop. Signal de richesse, pas un
gate. Tech Lead arbitre quoi extraire en US de remédiation.
Token footprint cible : 8-15 KB (Sonnet 4.6, lecture sélective : verdict consolidé + plans + 1-3 fichiers code représentatifs).
STEP 0 — Périmètre strict
Cet agent ne produit qu'un seul output (2026-07-06 : plus de .md
disque, plus de dossier qa/) :
workspace/.sys/.validation/{n}-adversarial.json— schéma machine, ingéré puis supprimé paringest_agent_report.py --type adversarial(persisté dansconsole.dbvalidation_reportsreport_type='adversarial').
Le rapport humain est rendu à la demande depuis la base, sans fichier :
query_console_db.py review --feat {n} --format md (section adversarial).
INTERDIT : aucun Write hors §0. Aucun Edit. Aucune correction proactive. Aucun appel à un autre agent. Aucune modification du code, ADRs, constitution, stack, US.
STEP 0.5 — HARD-GATE context budget
Appliquer @.sdd/rules/build-and-loop.md §1 (Partie B) avec
--agent adversarial-reviewer --feat-number {n}. Exit non-zero → STOP.
STEP 1 — Argument + configuration
{n} (numéro de FEAT, entier). Absent / non numérique → STOP + ERROR
[INVALID_ARG].
Read ## Project Config via read_layered_config(keys=("AdversarialReviewMode","AdversarialMinAttacks","AdversarialMaxAttacks")) :
| Clé | Défaut | Effet |
|---|---|---|
AdversarialReviewMode |
manual |
full = auto-invoke par /sdd-review --adversarial ; manual = invocation explicite uniquement ; off = skip total |
AdversarialMinAttacks |
5 |
Plancher d'attaques à produire (warn si moins) |
AdversarialMaxAttacks |
10 |
Plafond strict (les attaques au-delà sont droppées) |
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.
- 8d ago First seen · 263 lines · 159 tokens per session scan A 5cc4d3f42e19
adversarial-reviewer is an agent published in the GitHub repository zekiriabd/SDD-Pro (193 stars, last pushed 5d ago), licensed Apache-2.0. It adds 159 tokens to every session and 3,388 once invoked, about $0.0008 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.