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/brsbl/ottonomous/claude-mdgit clone --depth 1 https://github.com/brsbl/ottonomousWrote 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.
[](https://agentmods.dev/instructions/brsbl/ottonomous/claude-md)<a href="https://agentmods.dev/instructions/brsbl/ottonomous/claude-md"><img src="https://agentmods.dev/badge/instructions/brsbl/ottonomous/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01291 | $0.01291 |
| Opus 5 | $0.00646 | $0.00646 |
| Sonnet 5 | $0.00258 | $0.00258 |
| Haiku 4.5 | $0.00129 | $0.00129 |
Grade A, and why
ottonomous 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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ottonomous repository guide
Product contract
Ottonomous publishes exactly four provider-agnostic skills:
speccreates or revises a researched, independently reviewed product spec, writes it to the caller's destination, and ends with a link.reviewruns parallel P0-P2 code review, validates false positives, and can implement caller-approved fixes.buildimplements a caller-supplied spec through bounded delegation, integration, and repeated verification.summarycreates a decision-focused Moss Markdown change summary led by the problem statement, outcomes, trade-offs, and platform implications.
Each skill is independently invocable. Do not introduce a required sequence,
fixed working directory, resumable workflow state, or hidden persistence.
Callers may provide references, working locations, output destinations, and
delivery constraints. The one default artifact location is summary's visible
Moss workspace note; it is a public delivery contract, not workflow state.
Skill behavior
spec
Preserve its quality loop: working-context inspection, current primary-source research when needed, collaborative requirements interview, one canonical decision-led spec, technical-product-manager review, and user resolution of genuine decisions before delivery.
The source may be an idea, inline draft, or exact reference. The destination and format are caller-supplied; an existing spec can be its own destination. If no destination is available, ask for one before drafting. Write the complete reviewed spec there, verify it, and end with only a clickable link. Do not show the full spec inline or request a sign-off.
review
Preserve the review semantics:
- Architectural and implementation scopes may run in parallel.
- Findings use P0-P2 and must be concrete, actionable, and introduced by the reviewed change.
- The false-positive validator reads full source context and never adds new findings.
- Fix mode uses caller-supplied, caller-approved findings and verifies the integrated result.
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.
- 5d ago First seen · 159 lines · 1,291 tokens per session scan A a1563db3e94b
ottonomous CLAUDE.md is an instructions file published in the GitHub repository brsbl/ottonomous (15 stars, last pushed 11d ago), licensed MIT. It adds 1,291 tokens to every session, about $0.0065 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.
Other instructions, from other repositories
docflow AGENTS.md
Instructions for MedAdemBHA/docflow, a project described as: Documentation memory for AI coding agents—route project knowledge, reduce repeated context loading, and validate living Markdown docs.
trigger_tree CLAUDE.md
Claude Code instructions for Hedde/trigger_tree: Keep this file as a router. Read only the references needed for the task.
living-manual CLAUDE.md
Instructions for dougstanford/living-manual, covering living-manual, start of every session, how work lands — non-negotiable, user's manual (living-manual) and releasing.
pitchdocs GEMINI.md
Instructions for littlebearapps/pitchdocs, covering pitchdocs, tech stack, commands, conventions and key paths.
claude-sdd-plugin CLAUDE.md
Claude Code instructions for viamus/claude-sdd-plugin, covering sdd orchestrator — plugin context, fundamental rules, workflow, pipeline (automated by sdd-gen) and plugin structure.
m2ui-skill copilot-instructions.md
Copilot instructions for martysama0134/m2ui-skill, covering m2ui — metin2 ui code generator, mode detection, reference documentation, two ui styles and critical code generation rules.