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/implementWrote 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/implement)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/implement"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/implement/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/implement"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/implement.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 | $0.00013 | $0.05775 |
| Opus 5.5 | $0.00005 | $0.02310 |
| Sonnet 5.5 | $0.00003 | $0.01155 |
| Haiku 4.5 | $0.00001 | $0.00577 |
Grade A, and why
implement 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 11d 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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement one eligible task from the assigned stable SPEC.md. Stability names its identity, not a fixed folder;
resolve its current route through the manifest and native lifecycle tools. One invocation
owns one task and one durable writer lane.
For v3 work, workbench/manifest.json is the support-path authority; the
manifest-aware spec tool resolves the assigned SPEC.md. Do not write a root
specs/ fallback or copy the global core into a project-local skills tree.
Authorized room-local extensions follow the Runbook ownership procedure.
1. Situate the slice
Verify the repository root, branch, remote, upstream, and dirty state. Read the
nearest AGENTS.md and its RUNBOOK.md, then run:
node workbench/tools/spec-workbench.mjs doctor
node workbench/tools/spec-workbench.mjs next --json
node workbench/tools/spec-workbench.mjs show S-###
Continue when the explicitly assigned task is ready or resumable and the
working tree can be safely attributed. next supports owner-directed pickup;
it does not override an explicit assignment. Use the stance assigned in SPEC
and TASK, and investigate within that task without inventing another queue item.
Resolve the Task's TASK.md through the Spec and manifest; read its destination,
blockers and receipt rows, plus the objective's notepad. If already in progress,
verify its owner, branch and achieved proof and resume without a second claim.
For a planned or table-backed packet, follow the Runbook's native activation
and conversion route only under existing authorization; retain the existing
Task ID. Never manufacture a replacement Task to avoid a blocker.
Name the authorized endpoint before editing: scoped Worker handback, a draft candidate, or reviewed integration, as the request and controls actually allow. A ready slice must belong to this writer; claim it:
node workbench/tools/spec-workbench.mjs claim S-### --agent NAME
The slice is situated when one eligible task, its acceptance boundary, its public testing seam, and its single writer are explicit.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed · +11 lines 79184de43972
- 12d ago Changed · +385 lines 7896c66de573
- 1mo ago Changed · -1 lines b4f2db29a623
- 1mo ago Changed · +1 lines e3a274cadb14
- 1mo ago Changed · +7 lines 8c27998bcdc8
- 1mo ago First seen · 93 lines · 13 tokens per session scan A 98b5d57bb706
implement is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 5,775 once invoked, about $0.0001 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
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…