Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mtarcure/claude-vibe-squad/main/.agents/skills/rule8-truth-gate/SKILL.mdgit 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/rule8-truth-gate)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/rule8-truth-gate"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/rule8-truth-gate/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/rule8-truth-gate"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/rule8-truth-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 81 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 82 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00064 | $0.01457 |
| Opus 5 | $0.00032 | $0.00728 |
| Sonnet 5 | $0.00013 | $0.00291 |
| Haiku 4.5 | $0.00006 | $0.00146 |
Grade A, and why
rule8-truth-gate 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule-8 Truth Gate
Combines the release-gate portions of claim-verification + citation-audit into one invokable check. Given a
deliverable's claims plus a returned citation / grounding-result set, it decides whether each load-bearing claim
is supported by a returned citation within the requested recency window, and emits a machine-checkable gate
record. A model cutoff is never verification evidence; grounding is a first-class stage, not a hope that the
reviewer supplies evidence later.
Procedure
- Decompose the content into discrete claims and mark each load-bearing (a conclusion the deliverable
depends on) or non-load-bearing / backgrounded. Classify each:
fact | quote | calculation | forecast | opinion | inference. Every load-bearing claim is gated — INCLUDING a load-bearing inference (a reasoned conclusion the deliverable rests on): an inference is NOT exempt because it is framed as reasoning rather than quoted — its supporting premises/evidence must map to returned citations, or it isunverifiable→needs_tool. Only a genuine opinion, or non-load-bearing / backgrounded reasoning, passes ungated. - Ground each load-bearing web/factual claim: route a grounding worker (Gemini
Google Search groundingor a research-namespace handoff) that returns a typed evidence bundle of citations/search results. If no grounding tool is callable for a load-bearing claim, that is a capability gap → setneeds_tool: true(a separate axis). A claim whose callable grounding tool returned nothing supporting is unresolved evidence, not a missing tool → it drives HOLD/FAIL, notneeds_tool. - Map claim → citation (
claim_to_citation): each load-bearing claim — AND each load-bearing inference, via the evidence for its premises — must map to a specific returned citation, not to model prose. Read the source and confirm it SUPPORTS the claim/premise (not merely mentions the topic); for an inference, also confirm the reasoning is valid over the mapped premises. Preserve quote context. - Resolve + date-check every citation (
date_window): resolve each citation, record accessed-at; a citation that 404s or was invented is unverifiable. Confirm publication/event dates fall inside the requesteddate_window, and check for retractions/corrections. A claim supported only by a citation outside the window is not fresh-supported. - Reproduce arithmetic; check units and internal consistency. Label vendor/provider performance claims as vendor claims unless reproduced on a Vibe-Squad benchmark.
- Reject unsupported (
reject_unsupported): any load-bearing claim OR load-bearing inference that does not map to an in-window returned citation is dropped or the gate fails — never PASS on prose or on unbacked reasoning. When grounding was callable, an unmapped or out-of-window load-bearing item drives the result to FAIL (or HOLD pending more evidence), neverneeds_tool—needs_toolis reserved for the capability-absent case. - Emit the gate record (see below).
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.
- 11d ago First seen · 84 lines · 64 tokens per session scan A b548da5f7ccf
rule8-truth-gate is a skill published in the GitHub repository mtarcure/claude-vibe-squad (148 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 1,457 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
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-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.