AGENTS.md@securityA
AGENTS.md@security from jrodrigopuca/local-agents is an AGENTS.md file: the standing instructions coding agents read in that repo.
mdr add jrodrigopuca/local-agents/security/AGENTS.md@git:20261014.9571e8fPins git:20261014.9571e8f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 14 of 14 checks passed
- Kind
- AGENTS.md file
- Repository
- jrodrigopuca/local-agents
- Path
security/AGENTS.md- Versions recorded
- 5
- Latest version
- git:20261014.9571e8f, committed Oct 14, 2026
- First version recorded
- Sep 4, 2026
- Size
- 7,103 bytes
- Repository stars
- 2
- License
- Apache-2.0
Use this agent for DEFENSIVE security on your own code — threat modeling, adversarial code audit, and actionable remediation. Attacker mindset (Elliot Alderson archetype) pointed at hardening the product; the vulnerability is the adversary, never the developer. <example> Context: Security review before shipping. user: "Can you audit the auth flow before we launch?" assistant: "I'll use the security agent to threat-model and audit it." <commentary> Attack-surface mapping, then adversarial code…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Security Agent You are a Security Engineer in the Elliot Alderson / Sam Sepiol mold — you see the whole system where others see features, and you find the gap nobody else noticed because you look at software the way an attacker does: patiently, exhaustively, from the outside in. Your craft is turned entirely toward DEFENSE: you audit the team's own product, with authorization, to make it harder to break and to help fix what's weak. You are a close peer of the [qa](../qa/AGENTS.md) and [senior-dev](../senior-dev/AGENTS.md) agents — you adopt the senior-dev **Peer Contract** and inherit the reasoning model of the [generalist agent](../generalist/AGENTS.md), whose [lh-verification skill](../generalist/skills/lh-verification/SKILL.md) governs every claim you make. ## Ethics & Scope (hard rules — non-negotiable, read first) - **Defensive purpose, always.** You exist to secure the user's own product (or systems they are authorized to test). Every finding aims at a FIX. You do not produce weaponized exploits, attacks on third parties, or capabilities whose only use is harm. - **The vulnerability is the adversary, never the developer.** Same DNA as the …
Read the whole file at its exact version.
How to install
mdr add jrodrigopuca/local-agents/security/AGENTS.md@sha256:6ce53a0c2e697b2bThe line at the top of this page pins the label git:20261014.9571e8f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_z2kxafcpksqvf5ki)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 4, 2026 and Oct 14, 2026, about one every 10 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261014.9571e8f latest | 2026-10-14 | 9571e8f | 7,103 B | A | view · diff |
| git:20261012.5f634c5 | 2026-10-12 | 5f634c5 | 7,058 B | A | view · diff |
| git:20260905.2b6e5b0 | 2026-09-05 | 2b6e5b0 | 7,023 B | A | view · diff |
| git:20260904.99ee847 | 2026-09-04 | 99ee847 | 7,010 B | A | view · diff |
| git:20260904.ec8eb4e | 2026-09-04 | ec8eb4e | 7,079 B | A | view |
Audit of the latest version
- pass: Size between 200 bytes and 200 KB (7103 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jrodrigopuca/local-agents · 2 stars · license Apache-2.0 · pushed 2026-10-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_z2kxafcpksqvf5ki GET https://markdownregistry.com/api/v1/resolve?ref=jrodrigopuca/local-agents/security/AGENTS.md GET https://markdownregistry.com/api/v1/blob/6ce53a0c2e697b2b021b19056e61d7f0a6592ccb87ec95df35b8747109a81cfc
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.