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 mtarcure/claude-vibe-squad --skill program-rubric-lookupgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/program-rubric-lookup)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/program-rubric-lookup"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/program-rubric-lookup/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/mtarcure/claude-vibe-squad/program-rubric-lookup"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/program-rubric-lookup.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 | $0.00067 | $0.00855 |
| Opus 5.5 | $0.00027 | $0.00342 |
| Sonnet 5.5 | $0.00013 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
program-rubric-lookup 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Program Rubric Lookup
Map a finding to the target program's accepted vulnerability classes, severity language, payout rubric, and submission requirements.
Inputs
- The exact program policy or ruleset, with retrieval date and provenance.
- A concise finding statement, affected asset, impact, and prerequisites.
- Any explicit exclusions, safe-harbor conditions, or severity overrides.
Method
- Confirm the asset and vulnerability class are in scope before scoring.
- Extract the program's controlling severity rubric and any class-specific caps.
- Map each claimed impact to one quoted or precisely cited rubric clause.
- Record exclusions, prerequisites, and ambiguity separately from the score.
- Produce a conservative classification and identify what evidence would raise or lower it.
Acceptance
- Every classification cites the governing policy text and retrieval date.
- Scope, severity, payout eligibility, and submission requirements are distinct fields.
- Unsupported impact is marked unproven rather than inferred.
- Conflicts between generic scoring and program-specific rules resolve in favor of the program rules.
- The evidence contract is an output, not an assumption. Record, as separate fields: the program type and payout model; the authoritative target and what makes it authoritative (repo@commit, deployed address, host or build, binary hash); the PoC forms the program's own text accepts; and the forms it explicitly forbids, each tied to the clause that says so.
- Where the program is silent, write "not stated" — never infer a restriction. A generic or internal grading heuristic is not a program rule. Do not conclude from one that a live-chain transaction, a particular tool, or a production crash is required when the program's published text asks only for a working proof of concept. Inferring such a requirement has already sent a campaign chasing evidence nobody asked for.
Payout topology (AUD-11)
There is no universal severity-to-dollar table — rewards are program-specific. Record, alongside the rubric:
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 · 71 lines · 67 tokens per session scan A e7b210c03ca9
program-rubric-lookup is a skill published in the GitHub repository mtarcure/claude-vibe-squad (165 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 855 once invoked, about $0.0003 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 2026-09-19.
Other skills, from other repositories
contributor-onboarding
Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
gh-file-issue
Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.
skill-installer
Install, update, trust, or inspect Codewhale skills from GitHub or local skill folders. Use when the user asks for available skills or wants a community skill installed.