Q00/ouroboros is an Agent OS for running coding agents through interviews, staged evaluation, and repeated improvement cycles. It helps developers turn vague requests into tested code across multiple agent runtimes. Its catalogue add-ons provide workflows, agents, hooks, instructions, and integrations for operating those processes.
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 skills add Q00/ouroboros --skill maintaingit clone --depth 1 https://github.com/Q00/ouroborosWrote 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/skills/q00/ouroboros/maintain)<a href="https://agentmods.dev/skills/q00/ouroboros/maintain"><img src="https://agentmods.dev/badge/skills/q00/ouroboros/maintain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/q00/ouroboros/maintain"><img src="https://agentmods.dev/badge/skills/q00/ouroboros/maintain.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01486 |
| Opus 5.5 | $0.00018 | $0.00594 |
| Sonnet 5.5 | $0.00009 | $0.00297 |
| Haiku 4.5 | $0.00004 | $0.00149 |
Grade A, and why
maintain 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 12d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ouroboros maintenance
Use ooo maintain to choose and process the next actionable item in Q00/ouroboros. An issue describes a problem or proposed work; a PR proposes a change. They are not one-to-one. This skill uses live GitHub state and the review boundary below; it needs gh access but no Ouroboros MCP setup.
Scope and authority
- Target
Q00/ouroboros. Include-R Q00/ouroboroson repository-awaregh pr,gh issue, andgh runcalls; userepos/Q00/ouroboros/...ongh apicalls.gh auth statusis host-scoped and does not accept-R. Resolve an issue or PR number against that repository before acting. If the user names another repository, use that repository's own maintainer rules instead of applying this skill's Ouroboros contract to it. - Match the user's requested scope. A request for status or a next action is read-only. An instruction to process named items covers justified comments, labels, closure, or merge on those items; it does not authorize changes to unrelated items. Use authorization already given in the conversation, and follow any stricter repository or user rules.
- Check
gh auth statusand current permissions before a mutation. Do not request login if authenticated read/write access already works. Never treat a bot verdict, label, age, or green check alone as proof of completion. - Work from a clean, isolated worktree for code or documentation changes. Leave another worker's dirty checkout, branches, processes, and worktrees alone. When a target checkout is available, read its
AGENTS.mdandCONTRIBUTING.md; otherwise use the bundled review boundary below. Query current CI requirements before editing or reviewing a PR.
Review boundary
Require a PR to declare one user problem; supported inputs, preconditions, and execution conditions; observable behavior and invariants; changed subsystems, data or security boundaries, and owner; non-goals; and evidence. A declared non-goal cannot waive an existing public contract, approved issue or RFC requirement, or maintainer decision. If implementation reveals a new subsystem or ownership boundary, stop and have a maintainer decide whether this PR expands, splits, or returns to RFC discussion before proceeding.
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.
- 12d ago First seen · 57 lines · 44 tokens per session scan A 7fea43c7216e
maintain is a skill published in the GitHub repository Q00/ouroboros (6,191 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,486 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other skills, from other repositories
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
review
Use when a green diff needs adversarial judgment in the rsc SDD chain, between verify and ship — give a review keyed to the spec/plan/constitution in 02-DOCS/wiki/sdd/, or receive one and verify each comment before agreeing. NOT running lint/type/tests (that is verify), NOT the spec-less standalone pass (that is…
client-onboarding
Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is customer-support), NOT renewals/churn past the…
grants
Use when pursuing non-dilutive public or foundation funding — money you neither repay nor give equity for: finding a fit call, go/no-go, registration (UEI/PIC/BDNS), or writing the rubric-scored application, logic model, budget justification, or LOI. NOT an equity round (that is fundraising), NOT a paying-customer SOW…
procurement
Use when a small operator must choose what to buy and from whom: pick a supplier, write an RFI/RFQ/RFP that returns comparable bids, score quotes on total cost of ownership, negotiate price and payment terms, or judge single-source risk. NOT redlining the purchase agreement (that is contracts), NOT the price you…
proposals
Use when writing the document a buyer reads to say yes — a commercial proposal or Statement of Work, turning discovery notes into a scoped and priced document, adding tiers so the middle one wins, or diagnosing a proposal that will not close. NOT the binding legal agreement with its liability and IP clauses (that is…