security-kb

A workflow for reading and proposing updates to a Security Knowledge Base, a repository of security evidence and findings tied to specific revisions.

In plain words
What is it for?
Use it to inspect the knowledge base, check its capabilities and status, validate proposed findings, and stage evidence-cited proposals.
Why use it?
It helps keep security claims evidence-based, tied to the correct code version, and within the repository’s required rules.

Skill for Claude CodeCodex

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 skills/dinosn/security-knowledge-base/security-kb
Any agent
npx skills add dinosn/security-knowledge-base --skill security-kb
Clone the repo
git clone --depth 1 https://github.com/dinosn/security-knowledge-base

Made for: Claude Code, Codex.

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,436 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00092 $0.01436
Opus 5 $0.00046 $0.00718
Sonnet 5 $0.00018 $0.00287
Haiku 4.5 $0.00009 $0.00144

Measured 3d ago against content hash 3a32ba398ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-kb 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 3d 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.

skills/security-kb/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use the Security Knowledge Base

Treat this skill as a portable workflow adapter. The selected repository's AGENTS.md, docs/protocol/v1.md, schemas, live capabilities, and kb runtime remain authoritative. Do not copy knowledge records into this skill.

Select the repository

  1. Locate the intended repository root by finding kb.json, AGENTS.md, and the kb entrypoint. If more than one candidate exists, do not combine them; select the boundary named by the user or ask which boundary to use.

  2. Work from that repository root. Read AGENTS.md and docs/protocol/v1.md completely.

  3. Run:

    ./kb --json capabilities
    ./kb --json status
    
  4. Require protocol major 1, agent_writes: ["proposals"], and false network, source_execution, and archive_extraction capabilities.

  5. Require the intended boundary_id and classification and integrity: ok. Note dirty state, but do not let unrelated worktree changes prevent read-only inspection. Before preparing or staging a new proposal, require a clean baseline and a non-null Git revision. After staging, the new proposal makes the worktree dirty by design; still validate that exact bundle and run lint. tenant_id in records and requests must equal boundary_id.

  6. Remember that boundary_id is not access control. Repository permissions, identities, storage, and separate checkouts enforce isolation.

  7. Stop and report any conflict between policy, schemas, protocol, and runtime.

For every command, check the process exit status and the JSON envelope. Require schema: skb.command-result/v1, supported versions, ok: true, and an appropriate trust value before using result. Inspect warnings. Preserve a failure's error.code, error.message, and error.details exactly.

Use bounded operations such as:

./kb --json list --type claims --limit 100
./kb --json list --type findings --limit 100
./kb --json search "QUERY" --type all --limit 50
./kb --json get OBJECT_ID
./kb --json source excerpt SOURCE_ID --start-byte 0 --length 4096

Read the full file on GitHub · 156 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 156 lines · 92 tokens per session scan A 3a32ba398ea4

Subscribe to this mod's changes

security-kb is a skill published in the GitHub repository dinosn/security-knowledge-base (9 stars, last pushed 21d ago), licensed MIT. It adds 92 tokens to every session and 1,436 once invoked, about $0.0005 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.