ai-agents: Skill for Claude Code

.claude/skills/ai-agents-external-claims/SKILL.md

ai-agents-external-claims is a skill for Claude Code from rjmurillo/ai-agents. It costs 126 tokens per session (2,791 once invoked), scanned B, original, MIT.

A verification guide for claims about vendors, external services, and third-party facts before they enter repository documents or other deliverables. It requires checking such claims against authoritative primary sources.

In plain words
What is it for?
Use it to verify external facts, trace claims to their original sources, check published numbers, and decide whether a claim is ready to include in an ADR, retrospective, memory, or report.
Why use it?
It reduces the risk of publishing unsupported numbers, attributions, or descriptions copied through unreliable summaries or citation chains.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; built for gstack.

This is rjmurillo/ai-agents's own configuration. It tells Claude Code how to work on ai-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agents configures →

Part of the project-toolkit plugin — 113 skills, 26 commands, 33 agents, 4 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to rjmurillo/ai-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rjmurillo/ai-agents/main/.claude/skills/ai-agents-external-claims/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 113 skills, 26 commands, 33 agents, 4 hooks.

Wrote 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.

agentmods badge for ai-agents-external-claims

README.md
[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-external-claims/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-external-claims)
Your own site
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-external-claims"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-external-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.

agentmods 80×15 button for ai-agents-external-claims

Your own site · 80×15
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/ai-agents-external-claims"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/ai-agents-external-claims.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,791 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.02791
Opus 5 $0.00063 $0.01396
Sonnet 5 $0.00025 $0.00558
Haiku 4.5 $0.00013 $0.00279

Measured today against content hash fb9c8038bf0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

ai-agents-external-claims scanned grade B with 1 finding 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 today.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test_structure_ai_agents_external_claims.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

| Flag-with-a-hypothesis provenance discipline | `.claude/rules/voice.md`, "Ownership: See Something, Say Something" | `grep -n "See Something" .claude/rules/voice.md` |
.claude/skills/ai-agents-external-claims/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-agents External Claims

This repo runs verification-based governance: a claim is true when a primary source, gate, or command output says it is, not when a vendor blog, a summary, or an agent asserts it. This skill is the front-gate for one specific claim class: external, vendor, and third-party assertions that arrive from outside the repo and are about to land inside a repo artifact (an ADR, a retro, a memory, a PR description, a session log) or an external deliverable. A wrong number un-cited from a published artifact costs more than the one or two fetches that would have caught it in the same pass.

Audience: a zero-context contributor (human or model) holding an external claim and deciding whether it may enter a durable artifact.

This skill is the discipline for verifying claims that originate OUTSIDE the repo. For proving an idea that originates inside the repo (hypothesis, probe, eval baseline), use ai-agents-research-methodology. For what counts as test evidence for code, use ai-agents-validation-and-qa. This skill hardens the general-purpose gstack claim-verification-before-ingest pattern into the repo's own artifact-ingest path.

Triggers

  • verify an external claim
  • check a vendor number
  • is this stat real
  • validate a third-party citation

Scope Boundaries

You want Use instead
Prove a repo-internal idea (probe, eval, ADR debate) ai-agents-research-methodology
Decide what counts as test evidence for a code change ai-agents-validation-and-qa
Scan a file for CWE-78 command injection security-scan
Stop a deliverable that no consumer demanded avoiding-manufactured-work
Gate work before it starts, not after it appears done front-gate-before-pipeline

Read the full file on GitHub · 131 lines

Files

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.

Changes

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.

  1. today Changed · +1 lines fb9c8038bf0b
  2. 8d ago First seen · 130 lines · 126 tokens per session scan B a5deab77d49f

Subscribe to this mod's changes

ai-agents-external-claims is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 2,791 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.