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/update-harnessWrote 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/update-harness)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/update-harness"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/update-harness.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.02773 |
| Opus 5 | $0.00014 | $0.01386 |
| Sonnet 5 | $0.00006 | $0.00555 |
| Haiku 4.5 | $0.00003 | $0.00277 |
Grade A, and why
update-harness 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Harness
Migrate one existing project to the current canonical LLM Workbench contract. Reconcile; do not overwrite. The target project's verified truth survives the template change.
Invocation
Use /update-harness [project path]. If the path is omitted, use the current
repository. Treat an explicitly requested version as the target only after the
canonical source confirms it exists.
Locate the checked-out LLM Workbench repository that supplies the target version before reading its templates or lifecycle tooling. This public product is self-contained and does not require a private machine path or external skill catalog.
Route selection
Choose the route before running anything. The migration has two exclusive modes, and only one of them touches a user-scoped skill:
--layout-onlymigrates the support root and reads skill presence only. It never installs, compares, marks, backs up, or replaces a skill. This is the default route for an already-adopted room and for any host whose discovery root the tool must not touch.--explicit-updateadditionally replaces Workbench-managed skills, and is used only when replacing them is the point of the run.
A same-named user-scoped skill that is shared, linked, or unmanaged is a reason
to choose --layout-only, not a workstation to reconcile first. The
skill-path-collision and unmanaged-skill refusals belong to
--explicit-update alone; a --layout-only run returns before either is
reached. Do not propose inventorying, backing up, or replacing an existing user
skill in order to retry a route you did not need.
1. Establish authority and source truth
- Read the applicable root and project-local
AGENTS.mdfiles completely. - Verify the target repository root, branch, remote, upstream, worktrees, and dirty state.
- Verify the canonical Workbench path, branch, remote, dirty state, and current
version from its live
README.mdorBLUEPRINT.md. - Read the canonical
templates/ADOPTION.md, the current control templates, and the upgrade section in the targetRUNBOOK.mdwhen it exists.
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 · +109 lines 3ef696a78017
- 8d ago First seen · 152 lines · 28 tokens per session scan A 5ce9a1cd4fcf
update-harness is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,773 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…