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 romarayt/raytsystem-public-os --skill raytsystem-run-reviewgit clone --depth 1 https://github.com/romarayt/raytsystem-public-osWrote 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/romarayt/raytsystem-public-os/raytsystem-run-review)<a href="https://agentmods.dev/skills/romarayt/raytsystem-public-os/raytsystem-run-review"><img src="https://agentmods.dev/badge/skills/romarayt/raytsystem-public-os/raytsystem-run-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/romarayt/raytsystem-public-os/raytsystem-run-review"><img src="https://agentmods.dev/badge/skills/romarayt/raytsystem-public-os/raytsystem-run-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.00434 |
| Opus 5.5 | $0.00025 | $0.00174 |
| Sonnet 5.5 | $0.00012 | $0.00087 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
raytsystem-run-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 1mo 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.
What it actually says
raytsystem Run Review
Inputs and outputs
- Accept one bounded target, exact file/source references, rubric, and stop condition.
- Return
PASSor sorted Critical/High/Medium findings with file:line, impact, evidence, and minimal fix.
Write scope
- Keep the reviewer read-only.
- Never edit files, acquire writer leases, promote, create Git refs, or perform external actions.
- Let the main agent resolve contradictions and own all writes.
Preflight
- Run
uv run raytsystem agent preflight --skill raytsystem-run-review --write --jsonlocally. - Run
agent subagent-checkbefore sending any excerpt to a reviewer surface. - Supply only the minimal non-sensitive target; do not leak the intended answer or suspected fix.
Workflow
- Inspect target contracts, implementation, tests, and declared gate evidence.
- Reproduce suspected failures read-only when safe.
- Rank findings by concrete impact; omit style-only commentary unless requested.
- Return summaries with source references, not raw logs.
Validation
- Verify source-of-truth boundaries, generation binding, idempotency, recovery, skipped gates, and docs/code agreement.
- Require evidence for every finding and distinguish untested risk from confirmed failure.
- Exercise evals
m3-review-goldenandm3-review-adversarial.
Recovery
- If quota/tool access ends, return reviewed scope, unresolved files/questions, and exact next read-only check.
- Do not call partial review success.
Stop and approval conditions
- Stop before writes, private hosted transfer, secrets, promotion, external mutation, or scope expansion.
- Report
unavailablewhen an independent surface cannot safely receive inputs; let the main agent continue sequentially.
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.
- 1mo ago First seen · 47 lines · 62 tokens per session scan A 830f62915e28
raytsystem-run-review is a skill published in the GitHub repository romarayt/raytsystem-public-os (149 stars, last pushed 20d ago), licensed Apache-2.0. It adds 62 tokens to every session and 434 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 2026-08-30.
Other skills, from other repositories
rubber-ducky
Use when you've planned a non-trivial change and are about to implement it, finished a complex or multi-file piece of work, just wrote tests, or are stuck on repeated failures or unexpected results — and any time the user says "rubber duck this", "rubber ducky", "get a second opinion", "sanity-check my plan", "poke…
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…
open-pr
Use when wrapping up a development task and getting a PR ready — runs local tests, creates a PR (if one doesn't exist) with a structured description template, conducts a code review via the review skill, and checks CI status with quick fixes. Trigger when the user says they're done with a feature, want to open a PR…
review
Use when user invokes /review to review code changes. Also triggers on "review my code", "check this PR", "look at my changes". Accepts a PR number (e.g. /review 123), a path filter (e.g. /review src/auth/), or no argument (reviews current branch vs base). Produces structured per-file review with severity labels…
agent-review
Use in /implement after committing, inside the draft PR, to review the committed diff. Dispatches a dependency-free review subagent fed the diff + review criteria and returns structured findings (severity / location / problem / fix). The recipe drives the address→re-review loop with a human exit gate; the…
review
Adversarial design review of a System Design Doc. Interrogates the staff questions, finds the cost-explosion and failure risks, returns a verdict. Sensors and evals gate.