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-releaseWrote 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-release)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/workbench-release"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/workbench-release/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-release"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/workbench-release.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 | $0.03600 |
| Opus 5.5 | $0.00000 | $0.01440 |
| Sonnet 5.5 | $0.00000 | $0.00720 |
| Haiku 4.5 | $0.00000 | $0.00360 |
Grade A, and why
workbench-release 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 12d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workbench release
The release operations only this repository's maintainers run, 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.
Release Identity
A version label freezes when stamped, even before publication. A changed core bundle requires a new version label; preserve the prior manifest policy as an exact readable legacy row. Never redefine a stamped label silently. Only the owner publishes integration to main after applicable review.
The core machine catalog is coreSkills in the layout runtime; documentation
and tests derive its size from that catalog. The current candidate includes
save/promote while preserving checkpoint as a no-write compatibility notice.
The v3.1.4 eighteen-skill manifest policy remains readable as a frozen legacy
row. The owner explicitly waived the stamped-label rule for the v3.2.0
repair only (S-050/S-051, history; the v3.2.0 release Spec is superseded): its original twenty-skill policy remains readable,
while the repaired twenty-one-skill core is identified by source commit and
content hashes. This exception does not authorize publication.
Template Upgrade Release Gate
Before claiming a new version release-ready, apply the AGENTS Template Upgrade
Release Gate to Workbench_Template,
the example reference installation. Resolve the live repository identity even
when a local checkout or old remote is named Example_Workbench.
This is the required real-room test of update-harness.
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.
- 12d ago First seen · 269 lines · 0 tokens per session scan A 117e4c7bcac0
workbench-release is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,600 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship
Pre-release gate — run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
AI Release Guardian
Analyze a git diff, map affected risks, select the tests that matter, detect coverage gaps on changed lines, run configurable quality gates, and produce a go/no-go release report with cited evidence. Recommends only; never merges or deploys.