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 instructions/n-shadloo/secure-code-auditor/agents-mdgit clone --depth 1 https://github.com/n-shadloo/secure-code-auditorWhat 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 | $0.00996 | $0.00996 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
secure-code-auditor 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is a backend security skill. The canonical instructions live
in SKILL.md, which routes to the topic files under references/. An agent
that works in this repository loads SKILL.md first. Then it reads only the
references/*.md file(s) relevant to the task.
The primary integration is Claude (Anthropic Agent Skills). This file and
its siblings let other agents use the same content. They are pointers, not
copies. Where anything here disagrees with SKILL.md, SKILL.md wins. The
current version is recorded in the SKILL.md frontmatter
(metadata.version).
What this skill does
It reviews backend code for security issues, and it applies secure defaults while code is written. The corpus sits on the OWASP Top 10:2025 spine, with the API Security Top 10:2023 and ASVS 5.0 beside it. Each reference carries a stack-neutral principle layer and a deep Django and DRF layer. Every control is stated in a review form and a write-time form together.
The coverage spans the whole backend. It runs from the audit workflow and the
entry-point inventory, through access control, authentication, injection,
integrity, cryptography, and configuration. It reaches the API surfaces that
are not DRF routes. It covers the database and data-lifecycle layers,
service identity, deployment, file uploads, and agent and MCP tool surfaces.
It also covers the auditing agent's own access. The SKILL.md router names
each file's exact surface, so do not duplicate that list here.
Two modes
- Review-time. Audit existing code, and produce prioritized findings.
Each finding carries a severity, a location, a CWE and OWASP mapping, the
confirmed source-to-sink path with the protection that failed, and a fix.
The codebase stays read-only. Load
references/01-audit-workflow.mdbefore any topic file. It owns the sweep, and the topic files answer the questions the sweep generates. The report ends with what was not reviewed. - Write-time. Apply the standing secure-default contract while you generate code. Where a default conflicts with the request, apply the default and say so in one line. Close with a short security-decisions note rather than a findings report. The rule for each generation moment sits beside the control it completes, in the reference the router names.
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.
- yesterday First seen · 81 lines · 996 tokens per session scan A 34528572ed41
secure-code-auditor AGENTS.md is an instructions file published in the GitHub repository n-shadloo/secure-code-auditor (4 stars, last pushed 4d ago), licensed MIT. It adds 996 tokens to every session, about $0.0050 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 2026-08-31.
Other instructions, from other repositories
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
yapcap CLAUDE.md
Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.