Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/KaydenClark/LLM_Workbenchnpx agentmods add skills/kaydenclark/llm_workbench/workbench-room-checksWrote 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/kaydenclark/llm_workbench/workbench-room-checks)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/workbench-room-checks"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/workbench-room-checks/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/kaydenclark/llm_workbench/workbench-room-checks"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/workbench-room-checks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.08465 |
| Opus 5.5 | $0.00000 | $0.03386 |
| Sonnet 5.5 | $0.00000 | $0.01693 |
| Haiku 4.5 | $0.00000 | $0.00847 |
Grade A, and why
workbench-room-checks 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 yesterday.
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 — 607 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbench room checks
The checks this repository's maintainers run on the routes that create, adopt, upgrade and update a room, and on the producer's own contracts, moved here from the Runbook by the Contract Carrier Pointer-Brief Rewrite (S-004C TK-005K). Each section below is the procedure an operations index row in RUNBOOK.md points to, and it binds for that operation in this repository.
This is a maintainer skill: workbench/manifest.json declares it under maintainerSkills, so the release checks accept it beside the core bundle and no route installs it or lays it into a room (Maintainer skills). Commands run from the root of a clean checkout of this repository, and a path in backticks is relative to that root; a Markdown link resolves from this skill's folder.
GitHub Coordination Binding Inspection
Follow the GitHub coordination adapter procedure for read-only inspection of an explicit committed repository binding at an exact source SHA. It reports live access as unverified. This optional metadata command adds no Issue assignment or claim authority; ADR-000O remains operative until the separately reviewed cutover.
Skills lane check
The core skills ship inside every room at the manifest-declared skills lane,
workbench/skills, and the two declared discovery roots (.agents/skills
for Codex, .claude/skills for Claude Code) are tracked relative links into
that lane, so a fresh clone discovers the skills with no provider home and no
personal catalog. This repository's lane is the authoring source for
the 28 core skills listed in workbench/skills/README.md; every other room
receives receipt-backed copies from the release checkout:
node tools/workbench-skills.mjs install --project /absolute/project
node tools/workbench-skills.mjs verify --project /absolute/project
node tools/workbench-skills.mjs update --project /absolute/project --home /disposable-or-user-home --explicit-update
node tools/workbench-skills.mjs rollback --project /absolute/project --backup /path/recorded/in/receipt
node tools/test-skills-lane.mjs
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.
- yesterday Changed · +6 lines c6b61a33d88f
- 2d ago First seen · 601 lines · 0 tokens per session scan A 750510a33b90
workbench-room-checks is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,465 tokens. 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 2026-10-07.
Other skills, from other repositories
quality-scan
Run a scoped, read-only quality scan and report exact-candidate evidence, failures and frozen debt. Use for an ad-hoc gate sweep or release preparation; a static scan is not full release acceptance.
e2e-testing
Use when reviewing CI coverage, automated checks, or test strategy related to Implement end-to-end testing. Focus on whether the rule is continuously verified, not just documented.
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
migrate-vstest-to-mtp
Use this skill before answering, planning, or editing whenever .NET tests or CI are switching from VSTest to Microsoft.Testing.Platform (MTP), or an MTP migration behaves differently. Triggers include "switch from VSTest"; MSTest/NUnit/xUnit MTP enablement; OutputType=Exe only for test projects in…
ci
Configure Ginkgo for continuous integration — the recommended CLI flag set and the rationale for each flag (-r -p --randomize-all --randomize-suites --fail-on-pending --fail-on-empty --keep-going --cover --race --trace --json-report --timeout --poll-progress-after/-interval), invoking via go run to pin the CLI to…