fact-check

fact-check is a skill for Claude Code from AmethystLuna/embedded-workbench. It costs 100 tokens per session (585 once invoked), scanned A, original, MIT.

A lightweight process for checking claims in technical documents against the actual codebase. It checks names, paths, numbers, and whether proposed mechanisms are feasible.

In plain words
What is it for?
Reviewing design documents, architecture plans, technical proposals, and refactoring plans with evidence from source files.
Why use it?
It reduces the risk of approving plans that refer to missing files, incorrect APIs, wrong counts, or unsupported implementation details.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the embedded-workbench plugin — 8 skills, 4 agents, 1 hook shipped together

Install

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.

agentmods
npx agentmods add skills/amethystluna/embedded-workbench/fact-check
Any agent
npx skills add AmethystLuna/embedded-workbench --skill fact-check
Clone the repo
git clone --depth 1 https://github.com/AmethystLuna/embedded-workbench

Made for: Claude Code.

Or install embedded-workbench, the plugin that ships this one along with the rest of its 8 skills, 4 agents, 1 hook.

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 fact-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/amethystluna/embedded-workbench/fact-check.svg)](https://agentmods.dev/skills/amethystluna/embedded-workbench/fact-check)
Your own site
<a href="https://agentmods.dev/skills/amethystluna/embedded-workbench/fact-check"><img src="https://agentmods.dev/badge/skills/amethystluna/embedded-workbench/fact-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00100 $0.00585
Opus 5 $0.00050 $0.00293
Sonnet 5 $0.00020 $0.00117
Haiku 4.5 $0.00010 $0.00059

Measured 6d ago against content hash c58b8fe9b1c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

fact-check 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.

skills/fact-check/SKILL.md · 58 lines

What it actually says

Fact Check (fallback)

Lightweight claim verification built into this plugin. Use it when the full logicprobe plugin is not installed — it checks every verifiable claim in a document/plan against the codebase with evidence, without model escalation.

When to use

  • Design docs, architecture specs, technical proposals, refactoring plans that name APIs, types, files, enums, counts, or mechanisms.
  • Proactively when a plan will be approved (plan-mode gate) and logicprobe is unavailable.

What to verify (per claim)

Claim type Method
Numeric claims (counts, sizes, frequencies) grep -c / grep -rn
API/type/enum names Extract actual signatures/values from headers
File paths and line numbers Confirm existence and content
Mechanism feasibility Check language standard / compiler support

Process

  1. Enumerate every verifiable claim (quote it verbatim).
  2. Verify each against the codebase with evidence (file:line + excerpt).
  3. Output per claim: claim → evidence → verdict.

Output format

  • Claim:
  • Evidence: <file:line + grep/read excerpt>
  • Verdict: confirmed | refuted | unverifiable
  • Correction direction (when refuted) — never fix inline.

Append a ## Plan Verification block:

## Plan Verification
- **Mode**: fact-check (fallback — logicprobe plugin not installed)
- **Claims checked**: [N] confirmed, [M] refuted, [K] unverifiable
- **Escalation**: model verification NOT run (requires logicprobe plugin)

Boundaries

  • No executable model verification — no state-space exploration, no harness.
  • State machines (≥3 states), ACK/NACK/retry/timeout logic, lock/unlock ordering, and "always"/"never"/"guaranteed" claims require the logicprobe plugin: install it (see .dsh/INSTALL.md) or tell the user verification is degraded to manual mode for those claims.
  • Checking a claim is not a security audit; being checked ≠ being safe.
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. 6d ago First seen · 58 lines · 100 tokens per session scan A c58b8fe9b1c5

Subscribe to this mod's changes

fact-check is a skill published in the GitHub repository AmethystLuna/embedded-workbench (8 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 585 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

cordis-plugin-development

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider…

deepseek-ai/deepseek-harness · 80 tokens

record-browser-gif

Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply. Use when asked to make, record, or…

deepseek-ai/deepseek-harness · 106 tokens

editing-cordis-compositions

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…

deepseek-ai/deepseek-harness · 69 tokens

dsh-pre-push-checks

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on a deepseek-harness branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository…

deepseek-ai/deepseek-harness · 68 tokens

dsh-merging-stacked-prs

Use when landing a stack of dependent GitHub PRs (A ← B ← C, where each bases on the one below) onto master, merging a PR whose base is another open PR's branch, or whenever a request mentions "stacked PRs", "PR stack", "dependent PRs", or merging several related PRs in sequence. Requires every same-repository…

deepseek-ai/deepseek-harness · 118 tokens

dsh-doc

Create, restructure, review, audit, or migrate DeepSeek Harness Markdown documentation, package READMEs, and the documentation website using audience-first hierarchy, kind-mapped YAML metadata, bilingual line alignment, summary/contents navigation, progressive user-to-developer detail, executed-operation…

deepseek-ai/deepseek-harness · 95 tokens