Borrowing it
Nothing to install: this file belongs to Srajangpt1/ai-security-crew. 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/Srajangpt1/ai-security-crew/main/AGENTS.mdgit clone --depth 1 https://github.com/Srajangpt1/ai-security-crewWrote 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/instructions/srajangpt1/ai-security-crew/agents-md)<a href="https://agentmods.dev/instructions/srajangpt1/ai-security-crew/agents-md"><img src="https://agentmods.dev/badge/instructions/srajangpt1/ai-security-crew/agents-md/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/instructions/srajangpt1/ai-security-crew/agents-md"><img src="https://agentmods.dev/badge/instructions/srajangpt1/ai-security-crew/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01250 | $0.01250 |
| Opus 5.5 | $0.00500 | $0.00500 |
| Sonnet 5.5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
ai-security-crew AGENTS.md 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 13d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Audience: LLM-driven engineering agents
This file provides guidance for autonomous coding agents working inside the AI Security Crew repository.
Repository map
| Path | Purpose |
|---|---|
src/mcp_security_review/ |
Library source code (Python ≥ 3.10) |
├─ providers/sca/ |
Package registry and OSV vulnerability providers |
├─ servers/ |
FastMCP server implementations |
├─ library/ |
Threat library: components, threats, countermeasures (YAML) |
├─ security/ |
Code review context and threat modeling |
├─ guard/ |
Runtime guard for coding agents (asc-guard): hook CLI, Jev client, policy |
└─ utils/ |
Shared utilities (env, logging, lifecycle) |
tests/ |
Pytest test suite with fixtures |
scripts/ |
Guideline and assessment helper scripts |
Security tool workflow
Note: This workflow is also delivered to end users automatically via the MCP server's
instructionsfield on connect. Changes here should stay in sync withservers/main.py.
Before starting any coding task
- Call
general_lightweight_security_reviewwith the task description. It returns a menu of components. Call it again withcomponentsset to the ids this change adds or modifies (usually 2 to 5) (anddata_handledfor credentials, payments, or personal data) to get the threats and countermeasures. - If the task comes from a ticket or page link (Jira, Confluence, Linear, GitHub issues, and so on), fetch it first with the matching MCP server you have connected and pass its details as the task description.
- For significant new features (auth, file handling, external integrations), also call
threatmodel_perform_threat_modelwith the samecomponents.
When adding or updating packages
Run both steps before writing code that uses the new packages:
- Verify packages exist — call
sca_verify_packages. Fix any invalid packages before proceeding. - Scan for vulnerabilities — call
sca_scan_dependenciesin parallel withgeneral_verify_code_security, passing the packages. Each finding has areachability_check(affected symbols and a question). Answer it from your own code and act:- symbols are used, or you cannot tell → upgrade to the fixed version or avoid the symbol before continuing
- symbols are not used → note it and continue; consider upgrading anyway
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.
- 13d ago Changed · +1 lines · +30 tokens per session 4e5c3a57d2df
- 17d ago Changed · +10 tokens per session 87e5466e760b
- 18d ago Changed · -1 lines · +103 tokens per session 0d2b5fef394c
- 19d ago Changed · +49 tokens per session 72b43d148000
- 1mo ago First seen · 122 lines · 1,058 tokens per session scan A 8fd6cd45a3ce
ai-security-crew AGENTS.md is an instructions file published in the GitHub repository Srajangpt1/ai-security-crew (73 stars, last pushed 12d ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0050 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.