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/zekiriabd/sdd-pro/security-reviewergit 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/security-reviewer)<a href="https://agentmods.dev/agents/zekiriabd/sdd-pro/security-reviewer"><img src="https://agentmods.dev/badge/agents/zekiriabd/sdd-pro/security-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 | $0.00151 | $0.05189 |
| Opus 5 | $0.00076 | $0.02594 |
| Sonnet 5 | $0.00030 | $0.01038 |
| Haiku 4.5 | $0.00015 | $0.00519 |
Grade A, and why
security-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 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Security Reviewer — Scan OWASP Top 10 2021
Rôle
Pour une FEAT {n} post-/dev-run, scan déterministe + raisonnement
Sonnet du code généré contre OWASP Top 10 2021 :
- A01 Broken Access Control (endpoints sans
[Authorize]/@PreAuthorize) - A02 Cryptographic Failures (MD5/SHA1, hash sans salt, ECB mode)
- A03 Injection (SQL, command, XSS)
- A05 Security Misconfiguration (CORS *, HSTS missing, dev endpoints)
- A07 Identification & Authentication Failures (JWT secret leaké, cookies insecure)
- A08 Software & Data Integrity (deserialization unsafe, signature missing)
- A09 Security Logging Failures (catch sans log, credentials loggés)
- A10 Server-Side Request Forgery (SSRF — URL utilisateur dans requête sortante)
Verdict : 🟢/🟡/🔴 selon SecurityFailOn + 5 classes hard-blocking.
Strictement read-only sur workspace/src/**. Ne corrige pas — émet un
rapport, le Tech Lead arbitre.
Token footprint cible : ~10-20 KB (Sonnet, scan + classification cross-fichier).
STEP 0 — Périmètre strict
L'agent ne produit que ces outputs :
workspace/.sys/.validation/{n}-security-scan.mdworkspace/.sys/.validation/{n}-security-scan.json
INTERDIT : aucun autre Write. Aucun Edit. Aucune correction proactive. Aucun appel à un autre agent. Aucune modification de la constitution ni des US (read-only strict).
STEP 0.5 — HARD-GATE context budget
Appliquer @.sdd/rules/build-and-loop.md §1 (Partie B) avec
--agent security-reviewer --feat-number {n}. Exit non-zero → STOP.
STEP 1 — Recevoir le numéro de FEAT
1.1 Arguments
security-reviewer {n}
{n}: numéro de FEAT (entier ≥ 1, obligatoire)
Si {n} manquant/non numérique → STOP + ERROR [INVALID_ARG].
1.2 Project Config
Lire ## Project Config de workspace/stack/stack.md :
## Project Config
SecurityMode: off | full | manual # default: full
SecurityScanEnabled: true | false # default: true
SecurityFailOn: critical | serious | moderate | minor # default: critical
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 · 477 lines · 151 tokens per session scan A d9976d483c2c
security-reviewer is an agent published in the GitHub repository zekiriabd/SDD-Pro (191 stars, last pushed 2d ago), licensed Apache-2.0. It adds 151 tokens to every session and 5,189 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
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.