agentic-security CLAUDE.md

A Claude Code instruction file for the agentic-security project. It documents the repository layout, how to build and test, the pre-push checks, and how to produce signed, portable evidence.

In plain words
What is it for?
Use it when working in the agentic-security repository and you need its build, test, pre-push, or evidence procedures.
Why use it?
Project-specific instructions reduce uncertainty about expected workflows and validation. They help contributors follow the repository's security and release requirements.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/clear-capabilities/agentic-security/claude-md
Clone the repo
git clone --depth 1 https://github.com/Clear-Capabilities/agentic-security
Per session 6,270 This file is loaded in full into every session.
When invoked 6,270 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.06270 $0.06270
Opus 5 $0.03135 $0.03135
Sonnet 5 $0.01254 $0.01254
Haiku 4.5 $0.00627 $0.00627

Measured 2d ago against content hash bc2c1412b412, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

agentic-security CLAUDE.md scanned grade B with 1 finding 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Wipe scan state before benchmarking.** `.agentic-security/` dirs accumulate inside scanned `pre/`/`post/` trees and can mask results. `find bench/cve-replay -type d -name .agentic-security -prune -exec rm -rf {} +` b

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

CLAUDE.md · 165 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 2d ago First seen · 165 lines · 6,270 tokens per session scan B bc2c1412b412

Subscribe to this mod's changes

agentic-security CLAUDE.md is an instructions file published in the GitHub repository Clear-Capabilities/agentic-security (90 stars, last pushed 3d ago), with no licence file. It adds 6,270 tokens to every session, about $0.0314 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.