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 raghatatepiyush/ringmaster --skill ownership-reviewgit clone --depth 1 https://github.com/raghatatepiyush/ringmasterWrote 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/raghatatepiyush/ringmaster/ownership-review)<a href="https://agentmods.dev/skills/raghatatepiyush/ringmaster/ownership-review"><img src="https://agentmods.dev/badge/skills/raghatatepiyush/ringmaster/ownership-review/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/raghatatepiyush/ringmaster/ownership-review"><img src="https://agentmods.dev/badge/skills/raghatatepiyush/ringmaster/ownership-review.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 | $0.00186 | $0.02327 |
| Opus 5 | $0.00093 | $0.01163 |
| Sonnet 5 | $0.00037 | $0.00465 |
| Haiku 4.5 | $0.00019 | $0.00233 |
Grade A, and why
ownership-review 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ownership Review
Most code review asks one question: is the code correct and safe? Ringmaster already answers that — the Security Gate hunts vulnerabilities and the code-review pipeline hunts defects. This skill exists for the other question, the one the AI era makes urgent and no market tool answers well:
Does the human who is about to take 100% responsibility for this change actually understand it?
When AI writes the code, the old path to understanding — writing it yourself — is gone. A developer can ship a diff they've only skimmed and honestly believe they've "reviewed" it. That's the gap that ends in a 2am incident nobody on the team can debug. This skill closes it: it reconstructs the developer's understanding through active recall, teaches wherever it finds a hole, and produces an auditable ownership sign-off so "I take responsibility for this" is backed by evidence instead of a vibe.
Two stances at once, and both matter:
- Be a rigorous examiner. Understanding is not having read the diff. Ask what only a person who genuinely grasps the change can answer. The sign-off is worthless if it's easy.
- Be a warm senior peer. This is a debrief between colleagues, not an exam that judges. Never shame a miss — a hole caught here is the whole point. The developer should leave more confident and more responsible, never smaller.
This skill is stack-independent and it does not re-implement bug detection — it stands on top of the tools that do.
The safety rails (inherited, non-negotiable)
The same rails the orchestrator enforces (hook-backed, hold under skip-permissions):
- You review; you never fix. Read-only. If comprehension surfaces a real defect, it goes into the record and back to the human — you don't patch it.
- You never commit, push, or write history. The only things this skill writes are the ledger's sign-off record and — on the human's say-so — an evidence draft. The human commits and ships.
- Never run anything against production. Execution grounding (running the change's own tests to confirm a claim) is DEV/UAT only.
- Never rubber-stamp. A sign-off that isn't honestly earned is worse than none — it launders responsibility. If the understanding isn't there, say so and stop.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 106 lines · 186 tokens per session scan A 2fb9c3a66369
ownership-review is a skill published in the GitHub repository raghatatepiyush/ringmaster (1 stars, last pushed 1mo ago), licensed MIT. It adds 186 tokens to every session and 2,327 once invoked, about $0.0009 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 skills, from other repositories
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
id-impact
Two advisory pre-merge reads of an infra-delivery change. (v2) The POLICY-RISK read — surface foundryplanmodel.parsepolicyfindings output {rule, resource, severity, gating} and distinguish hard-FAIL-shaped (gating==deny) vs ackable-shaped (gating==warn ∧ severity==high ⇒ freeze a policy:high-blast-ack {rule…
id-review
The infra-delivery two-lens advisory review procedure the generic agent runs at the infra-delivery review step (/foundry:id-review, infra-delivery review step / step 10 — the sd-review analog for infra). A PROCEDURE — it DISPATCHES the MERGED pr-reviewer general code lens (agents/pr-reviewer.md) ALWAYS, plus the…
sd-review
The two-lens advisory review procedure the generic agent runs at the software-delivery review step (/foundry:sd-review, software-delivery review step). A PROCEDURE — it DISPATCHES the MERGED pr-reviewer general code lens (agents/pr-reviewer.md) ALWAYS, plus the security-reviewer security lens…
mode-interactive
The interactive implementation posture (/foundry:mode-interactive) — the default lean direct loop. The operator drives edit→verify→merge in one accountable context; the operator reviews the diff at the merge button (the Regular-mode segregation). Sibling of mode-autonomous; they differ ONLY at the two ends (who paces…