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 jstoup111/ai-conductor --skill verify-claimsgit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/verify-claims)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/verify-claims"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/verify-claims/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/jstoup111/ai-conductor/verify-claims"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/verify-claims.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 | $0.00058 | $0.01956 |
| Opus 5 | $0.00029 | $0.00978 |
| Sonnet 5 | $0.00012 | $0.00391 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
verify-claims 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 10d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Decisive skills routinely state things as fact, or spec and build on assumptions, without ever marking them as uncertain or getting them confirmed. A wrong assumption that slips into a PRD, an ADR, a plan, or code is discovered late and is expensive to unwind.
This skill is the correctness discipline other skills apply at their decision points. It does two things:
- Calibrates claims. Non-trivial statements and theories carry a grounded confidence estimate (a %) with the basis for it. No confident-sounding prose hiding an unverified guess.
- Gates assumptions. Every assumption is surfaced explicitly. Any assumption that is load-bearing — one that, if wrong, changes what gets specced or built — is a hard block: the work does not proceed on it until the operator explicitly approves it.
It is deliberately cheap and quiet on high-certainty, low-stakes output, and loud exactly where a mistake would cascade. It does not replace domain review, conflict-check, or prd-audit — it sits before them, keeping unverified foundations out of the artifacts they inspect.
When This Applies
Apply the protocol whenever output is load-bearing — it will drive downstream work:
- A PRD functional requirement, an approach recommendation, or a track decision (
explore,prd) - An architectural claim or ADR (
architecture-review) - A story's acceptance criteria or a plan task (
stories,plan) - A statement about how existing code, an API, a schema, or a dependency behaves, when that
statement decides what to build (
tdd,debugging,manual-test) - Any answer to the operator that they may act on as fact
Skip it for casual conversation, restating something the operator just said, or trivially verifiable mechanics with no downstream blast radius. Ceremony on low-stakes output is noise — correctness matters at the load-bearing points, not everywhere.
Practices
1. Separate Claims From Assumptions
For the output under review, split its load-bearing content into two buckets:
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.
- 10d ago First seen · 163 lines · 58 tokens per session scan A 3a7a7ba34b3b
verify-claims is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 1,956 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…