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 parity-probegit 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/parity-probe)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/parity-probe"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/parity-probe/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/parity-probe"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/parity-probe.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 | $0.00033 | $0.00323 |
| Opus 5 | $0.00016 | $0.00161 |
| Sonnet 5 | $0.00007 | $0.00065 |
| Haiku 4.5 | $0.00003 | $0.00032 |
Grade A, and why
parity-probe 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 6d 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
Run the provider parity probe
Use the existing Markdown task board. This skill is an operator checklist, not a second runner, receipt format, or capability catalog.
Procedure
- Dispatch an ordinary Project or Bounty task through
shared/routing.md. Never invoke a provider CLI directly from this skill. - For each changed family, choose a representative specialist whose declared surface contains the capability being checked.
- Require the task to write its normal artifact and completion envelope. When relevant, have it execute one meaningful declared local CLI or utility MCP operation and one harmless negative check for an undeclared operation.
- For Kimi, keep utility MCP calls on the main lead's reviewed allowlist; native Agent children remain MCP-free.
- Accept the smoke result only when the normal board receipt, artifact, envelope, and focused test agree. Configuration, PATH output, or a listed tool alone is not proof that the operation worked.
Stop conditions
Stop and report the route as unproven when the task fails, the declared surface differs, the operation is denied or unavailable, or the provider requires an unapproved paid or credentialed action. Do not widen credentials, retry through another family, or bypass the board.
Keep private task output and credentials out of tracked files. Record only the concise pass/fail result and the affected family/capability in the phase evidence used for the final repository-wide audit.
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.
- 6d ago First seen · 23 lines · 33 tokens per session scan A a96c9b727563
parity-probe is a skill published in the GitHub repository mtarcure/claude-vibe-squad (142 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 323 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cw-dogfood
Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
issue-to-pr
Implement one bounded repository issue with normal host tools, prove the tested change through one scafld finalize wall, and optionally publish the exact pull request through scoped provider authority with readback.