security-knowledge-base CLAUDE.md

A Claude Code adapter for a local security knowledge base that stores evidence and reviewed proposals in JSON.

In plain words
What is it for?
It helps maintain and update the security knowledge base and its command-line interface while respecting the project contract.
Why use it?
It directs Claude Code to follow the repository’s single source of project rules instead of creating separate, conflicting instructions.

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/dinosn/security-knowledge-base/claude-md
Clone the repo
git clone --depth 1 https://github.com/dinosn/security-knowledge-base
Per session 36 This file is loaded in full into every session.
When invoked 36 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original 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 $0.00036 $0.00036
Opus 5 $0.00018 $0.00018
Sonnet 5 $0.00007 $0.00007
Haiku 4.5 $0.00004 $0.00004

Measured 2d ago against content hash d0c5e40f7792, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-knowledge-base CLAUDE.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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 6 lines

What it actually says

@AGENTS.md

AGENTS.md is the sole canonical repository contract. This file is only a Claude Code import adapter; do not add independent repository rules here.

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 · 6 lines · 36 tokens per session scan A d0c5e40f7792

Subscribe to this mod's changes

security-knowledge-base CLAUDE.md is an instructions file published in the GitHub repository dinosn/security-knowledge-base (9 stars, last pushed 21d ago), licensed MIT. It adds 36 tokens to every session, about $0.0002 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.