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 skills add rjmurillo/ai-agents --skill security-reviewgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/skills/rjmurillo/ai-agents/security-review)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/security-review"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/security-review/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/skills/rjmurillo/ai-agents/security-review"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.02419 |
| Opus 5.5 | $0.00041 | $0.00968 |
| Sonnet 5.5 | $0.00021 | $0.00484 |
| Haiku 4.5 | $0.00010 | $0.00242 |
Grade A, and why
security-review 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 22d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Review
This skill carries the same security-review knowledge the security agent
carries in its subagent system prompt, delivered instead as content read into
the parent's context and reasoned over inline. It is the skill form-factor
counterpart in the Issue #1875 eval (follow-on to ADR-058): same domain
content, one model call instead of a parent-to-subagent dispatch.
Canonical source: templates/agents/security.shared.md. The agent template is
the system of record for security-review behavior. This skill projects its core
review content (identity, threat-model protocol, CWE catalog, scoring, verdict
taxonomy). When the agent template changes, this skill is the stale projection
and must be re-synced from it.
Quoted canonical contract:
Before scoring any risk or assigning a severity, reason step-by-step through the threat model. Work through these three questions in order, and write the answers into the finding:
- What is the attack surface this change exposes? Name the concrete entry point (CLI argv, HTTP route, environment variable, file path, MCP tool parameter, agent prompt input).
- Who is the threat actor with the capability to exploit it? Name the actor class (anonymous internet user, authenticated low-privilege user, malicious internal contributor, compromised dependency, prompt-injected agent input) and what capability they need.
- What is the impact if exploited? Name the concrete loss (RCE on agent runner, secret exfiltration, agent goal hijack, data tampering of session log, denial of service on orchestrator).
Intentional divergence: the canonical security agent ends with
APPROVED / CONDITIONAL / BLOCKED for PR review. This skill ends with
IDENTIFY / OK / ESCALATE because the Issue #1875 form-factor fixtures score
the same verdict vocabulary used by eval-agent-vs-baseline.py.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed · +5 lines 429f24833638
- 25d ago Changed · +11 lines 2f442da6011a
- 1mo ago First seen · 219 lines · 103 tokens per session scan A b57012000d00
security-review is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 2,419 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.