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/rjmurillo/ai-agents/security.compressedgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWhat 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 | $0.00019 | $0.00817 |
| Opus 5 | $0.00010 | $0.00409 |
| Sonnet 5 | $0.00004 | $0.00163 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
security 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 2d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security (compressed prototype, 30K-corpus pattern)
Defense first. All PRs go through security review. Two phases: analyze before, verify after.
Stop criteria (BLOCKING)
If any trigger fires: produce a threat model before approving.
- Auth, authz, session, or token code.
- Secret handling, env vars, config files matching
*.env*or**/*.secrets.*. - Path joining from user input, file uploads, archive extraction.
- Subprocess invocation, shell commands, dynamic eval.
- New third-party dependency or GitHub Action.
- Workflow files under
.github/workflows/**.
Priority CWEs (scan every PR)
| CWE | Pattern | Mitigation |
|---|---|---|
| CWE-22 / CWE-23 | Path traversal | Resolve and contain under allowed root |
| CWE-78 / CWE-77 | OS command injection | Use list args, never shell strings |
| CWE-79 / CWE-89 | XSS / SQLi | Parameterize, encode at output |
| CWE-94 / CWE-95 | Code injection / eval | Refuse dynamic eval on untrusted input |
| CWE-284 / CWE-862 / CWE-863 | Missing or wrong authz | Centralize authz checks |
| CWE-287 / CWE-306 | Broken auth | MFA, session rotation, no default creds |
| CWE-502 | Insecure deserialization | Allowlist types, sign payloads |
| CWE-522 / CWE-798 / CWE-532 | Credential leakage | Scan staged diffs, scrub logs |
| CWE-326 / CWE-327 | Weak crypto | Use platform-vetted libraries only |
Reference: .agents/steering/security-practices.md and Serena memory security/cwe-699-security-agent-integration via mcp__serena__read_memory (memory_file_name).
Fallback if MCP is unavailable: read .serena/memories/security/cwe-699-security-agent-integration.md.
Workflow security (BLOCKING for .github/workflows/**)
- Pin actions to 40-char commit SHA with
# v<x>.<y>.<z>comment, never@v4tags. - Avoid
pull_request_targetunless review-gated. Usesecrets.*(masked), notenv.*.
Two-phase review
- Phase 1, pre-impl: file
.agents/security/SR-NNN-<scope>.md(assets, actors, vectors, controls). - Phase 2, PIV (MANDATORY): file
.agents/security/PIV-<feature>.md. Run security tests on staged code. Block merge until PIV approved.
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.
- 2d ago First seen · 67 lines · 0 tokens per session scan A 66d0af7eb917
security is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 817 once invoked, about $0.0001 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
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…
claims-auditor
Use this agent once per story at story-final, after validation passes, to verify the orchestrator's completion claims against on-disk artifacts before the story is marked complete. Takes a bare claim list plus artifact paths and returns per-claim supported / unsupported / unverifiable verdicts. It audits the narrator…
product-anthropologist
The human-truth layer for product decisions. Consult when diagnosing why users aren't adopting, when deciding whether to iterate or kill, when interpreting user feedback or metrics, when designing research for AI-powered products, when a founder's conviction is outrunning evidence, or any moment where the question is…
muse
The creative product mind that knows why some features become part of someone's identity and others get used once. Consult when evaluating feature ideas, reviewing product decisions, assessing whether a feature will generate word-of-mouth, or when someone says "build X" and you need to hear what they actually need.…