OODA-loop CLAUDE.md

Project instructions for OODA-loop, an autonomous AI-agent harness based on Observe, Orient, Decide, Act. They define its files, safety rules, session continuity records, skill layout, and configuration practices.

In plain words
What is it for?
Working on the harness, its skills and contracts, session state, plans, configuration, or rules for safe repository changes.
Why use it?
They give agents a consistent operating procedure across sessions and reduce risks such as exposing secrets or staging unintended files.

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/mataeil/ooda-loop/claude-md
Clone the repo
git clone --depth 1 https://github.com/mataeil/OODA-loop
Per session 313 This file is loaded in full into every session.
When invoked 313 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 $0.00313 $0.00313
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 3d ago against content hash e89d3477dc88, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

OODA-loop 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 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.

CLAUDE.md · 39 lines

What it actually says

CLAUDE.md — OODA-loop

Autonomous operations agent harness built on Boyd's OODA loop for Claude Code.

Structure

  • skills/ — All SKILL.md files (plugin auto-discovers these)
  • .claude-plugin/plugin.json — Plugin manifest
  • agent/contracts/ — Skill contract schema
  • agent/state/ — Runtime state (gitignored, per-project)
  • config.example.json — Config template for user projects

Code Rules

  • All files written in English
  • No secrets in config.json — use environment variable references only ($ENV_VAR)
  • Every skill must start with a HALT file check
  • No git add -A — explicit file staging only
  • Skills live in skills/{name}/SKILL.md, not in agent/skills/

Session Continuity

Design decisions, 7-Agent review results, and implementation plans from prior sessions:

  • .claude/context.md
  • .claude/plans/OODA-loop-plan.md

한국어 참고

Boyd의 OODA 루프 기반 자율운영 AI 에이전트 하네스.

코드 규칙

  • 모든 파일은 영어로 작성
  • config.json에 시크릿 직접 저장 금지 — 환경변수 참조만 ($ENV_VAR)
  • 스킬은 반드시 HALT 파일 체크로 시작
  • git add -A 금지 — 명시적 파일 스테이징만
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 · 39 lines · 313 tokens per session scan A e89d3477dc88

Subscribe to this mod's changes

OODA-loop CLAUDE.md is an instructions file published in the GitHub repository mataeil/OODA-loop (5 stars, last pushed 2mo ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 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.

Related

Other instructions, from other repositories