Citadel CLAUDE.md

Citadel CLAUDE.md is an instructions file for coding agents from SethGammon/Citadel. It costs 806 tokens per session, scanned A, original, MIT.

Instructions for Claude Harness, a system that coordinates coding agents, reusable skills, automated checks, and work that continues across sessions. A harness is the surrounding system that manages how an agent performs tasks.

In plain words
What is it for?
Use them when developing or maintaining the harness, its task-routing commands, parallel agents, project setup hooks, campaign tracking, or quality checks.
Why use it?
They explain where the system's skills, agents, hooks, and saved campaign state live so developers can work on the right part.

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/sethgammon/citadel/claude-md
Clone the repo
git clone --depth 1 https://github.com/SethGammon/Citadel

Wrote 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.

agentmods badge for Citadel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sethgammon/citadel/claude-md.svg)](https://agentmods.dev/instructions/sethgammon/citadel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sethgammon/citadel/claude-md"><img src="https://agentmods.dev/badge/instructions/sethgammon/citadel/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 806 This file is loaded in full into every session.
When invoked 806 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 $0.00806 $0.00806
Opus 5 $0.00403 $0.00403
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00081 $0.00081

Measured 4d ago against content hash 6b18765b648d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Citadel 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 4d 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.

CLAUDE.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Harness

An agent orchestration system for Claude Code. This repo IS the harness.

What This Is

The harness is a collection of skills, agents, hooks, and state files that enable Claude Code to operate autonomously on any codebase. It provides:

  • Intent routing (/do) that dispatches tasks to the right tool
  • Campaign persistence across sessions
  • Parallel agent coordination with discovery sharing
  • Automated quality enforcement through lifecycle hooks

Key Conventions

  • Skills live in skills/. Each skill is a directory skills/{name}/SKILL.md.
  • Agents live in agents/. They spawn as sub-processes with their own context.
  • Hooks live in hooks_src/. Installed per-project via scripts/install-hooks.js.
  • The init-project hook auto-scaffolds per-project state on session start:
    • .planning/ — campaign state, fleet sessions, intake, telemetry
    • .citadel/scripts/ — utility scripts (telemetry, coordination, compression)
    • .claude/agent-context/ — rules injected into sub-agents
  • Campaign state lives in .planning/campaigns/ (per-project).
  • Fleet session state lives in .planning/fleet/ (per-project).
  • Templates live in .planning/_templates/ (copied from plugin on init).
  • Configuration lives in .claude/harness.json (generated by /do setup, per-project).

Testing

Always run tests after modifying hooks or skills. Five levels:

Command What it checks When to run
node scripts/test-all.js Hooks + skill structure (fast, no LLM) After any change
node hooks_src/smoke-test.js Hooks only After hook changes
node scripts/verify-hooks.js Hook install + runtime (synthetic payloads, no LLM) After hook changes
node scripts/integration-test.js Full Pre→tool→Post pipeline sequences (no LLM) After hook changes
node scripts/skill-lint.js All SKILL.md structure After skill changes
node scripts/skill-bench.js Scenario file validity After adding benchmarks
node scripts/skill-bench.js --execute Live scenario execution Before shipping
node scripts/skill-bench.js --execute --verify-hooks Live execution + confirms hooks fired Before shipping

Read the full file on GitHub · 69 lines

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. 4d ago First seen · 69 lines · 806 tokens per session scan A 6b18765b648d

Subscribe to this mod's changes

Citadel CLAUDE.md is an instructions file published in the GitHub repository SethGammon/Citadel (916 stars, last pushed today), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-08-30.

Related

Other instructions, from other repositories