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 AmethystLuna/embedded-workbench --skill fact-checkgit clone --depth 1 https://github.com/AmethystLuna/embedded-workbenchWrote 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/amethystluna/embedded-workbench/fact-check)<a href="https://agentmods.dev/skills/amethystluna/embedded-workbench/fact-check"><img src="https://agentmods.dev/badge/skills/amethystluna/embedded-workbench/fact-check/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/amethystluna/embedded-workbench/fact-check"><img src="https://agentmods.dev/badge/skills/amethystluna/embedded-workbench/fact-check.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 | $0.00117 | $0.00617 |
| Opus 5.5 | $0.00047 | $0.00247 |
| Sonnet 5.5 | $0.00023 | $0.00123 |
| Haiku 4.5 | $0.00012 | $0.00062 |
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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fact Check (fallback)
Lightweight claim verification built into this plugin. Use it when the full
dsh-model-everything plugin — or its predecessor logicprobe — 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
- Enumerate every verifiable claim (quote it verbatim).
- Verify each against the codebase with evidence (file:line + excerpt).
- 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
logicprobeplugin: 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.
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.
- 5d ago Changed · +1 lines · +17 tokens per session 68f8c74c547e
- 1mo ago First seen · 58 lines · 100 tokens per session scan A c58b8fe9b1c5
fact-check is a skill published in the GitHub repository AmethystLuna/embedded-workbench (22 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 617 once invoked, about $0.0005 per session on Opus 5.5. 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
code-review-cn
A Chinese-language guide for reviewing code changes, pull requests, and diffs. It prioritizes correctness, resource cleanup, security, matching documentation, and tests before style.
refactor-safely
A safe code-refactoring guide for changing code structure while keeping its external behavior the same. Refactoring means reorganizing code without changing what it does.
pr-description
A writing guide for pull request descriptions. A pull request is a proposed set of code changes for review and merging.
review-changes
Review local code changes for concrete correctness, regression, security, and test gaps before shipping.
evo-memory-review
Review and curate an evo-subagent role's prefercmd.md and memory.md using evidence from actual runs. Use when evolution entries are stale, duplicated, contradictory, or too noisy.
knowledge-review
Review and improve a librocat library: raise link health, add missing architecture/decision concepts, and prepare knowledge changes as a Git PR. Use when the user asks to audit, clean up, or level-up an OKF bundle, when ingesting a code repo and wanting durable higher-level concepts on top of the mechanical Code File…