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.
npx agentmods add instructions/agenticdevops/aoh/claude-mdgit clone --depth 1 https://github.com/agenticdevops/aohWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00751 | $0.00751 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
aoh 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AOH — Agentic Ops Harness
Engine-neutral harness for agentic ops: packs of skills/roles/teams compiled to agent runtimes (Hermes, Claude Code, Codex today; Goose next). AOH organizes, packages, validates, adapts — it never executes. Runtimes execute.
Session bootstrap (ALWAYS, including after /clear or compaction)
Project memory lives in .planning/ markdown, outside the context window. Before any
work:
- Read
.planning/STATE.md— current position, next action, handoff notes - Read
.planning/ROADMAP.md— phase you're in, what "done" means - Consult
.planning/PROJECT.mddecisions table before proposing design changes — don't re-litigate decided questions; add new decisions to the table instead .planning/design/holds dated design reviews;.planning/codebase/holds architecture/structure/concerns maps;.planning/todos/pending.mdholds small items
Never rely on conversation memory for project state. If chat and .planning/ disagree,
.planning/ wins until the user says otherwise.
Session close (or any significant milestone)
Update .planning/ BEFORE ending work — this is how context survives /clear:
STATE.md: position, session log entry (date + what happened), next actionROADMAP.md: phase status changesPROJECT.md: new decisions with date + why- Commit
.planning/changes with the work they describe
Working style
Superpowers drives the loop — speed of iteration over ceremony:
- Creative/feature work → superpowers:brainstorming first
- All implementation → superpowers:test-driven-development (RED/GREEN/REFACTOR, no production code without a failing test)
- Bugs → superpowers:systematic-debugging
- Completion claims → superpowers:verification-before-completion (fresh command output or it didn't happen)
.planning/ is shared memory, not process. Do NOT spin up GSD phase ceremony
(PLAN.md, verification docs) here — GSD files that already exist (codebase/) are
read-only reference; keep formats compatible so GSD tools still work.
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.
- 2d ago First seen · 65 lines · 751 tokens per session scan A 24e9ccbd348f
aoh CLAUDE.md is an instructions file published in the GitHub repository agenticdevops/aoh (5 stars, last pushed 1mo ago), licensed MIT. It adds 751 tokens to every session, about $0.0038 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.
Other instructions, from other repositories
llm-wiki CLAUDE.md
Instructions for nvk/llm-wiki, covering llm-wiki development guide, testing, github auth and transport, structural tests (always run — no llm, instant) and behavioral evals (run when changing command logic).
agent-rules testing.instructions.md
Instructions for lirantal/agent-rules, covering testing guidelines for node.js applications, general testing principles, guiding principles, descriptive test naming (three-part structure) and structure tests by the aaa pattern.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.
clawock AGENTS.md
Instructions for KCNyu/clawock, covering agents.md - your workspace, every session, kcn 偏好, git hook (one-time setup per clone) and git auto-commit rules.
clawock CLAUDE.md
Instructions for KCNyu/clawock, covering claude.md, identity & user, required reads (every session, in order), what lives where and cron run loop (what openclaw fires).