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 agentmods add skills/kaydenclark/llm_workbench/implementnpx skills add KaydenClark/LLM_Workbench --skill implementgit clone --depth 1 https://github.com/KaydenClark/LLM_WorkbenchWhat 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 | $0.00013 | $0.00789 |
| Opus 5 | $0.00006 | $0.00394 |
| Sonnet 5 | $0.00003 | $0.00158 |
| Haiku 4.5 | $0.00001 | $0.00079 |
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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement one eligible ticket from the assigned stable SPEC.md. One invocation
owns one ticket and one durable writer lane.
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 tools/spec-workbench.mjs doctor
node tools/spec-workbench.mjs next --json
node tools/spec-workbench.mjs show S-###
Continue only when next returns the assigned ticket as ready or resumable and
the working tree can be safely attributed. For a ready slice, claim it:
node tools/spec-workbench.mjs claim S-### --agent NAME
The slice is situated when one eligible ticket, its acceptance boundary, its public testing seam, and its single writer are explicit.
2. Drive the behavior
Use red/green/refactor at the agreed seam:
- Add or change the smallest durable test that expresses the ticket behavior.
- Run it and observe the expected red failure.
- Implement the smallest change that turns it green.
- Refactor while the focused test stays green.
Run focused checks during the loop. Finish with every project-owned verification
command required by RUNBOOK.md. The behavior is driven when the expected red
and green results are named and the full required gate is green.
3. Document and checkpoint
Update the owning documentation named by AGENTS.md; keep capability state and
proof in the assigned spec and keep TASKBOARD.md a generated projection. Run
the required verification and create a truthful in-progress checkpoint while
the ticket remains in progress; commit and push it, then compare the local SHA
with the remote branch SHA.
Record the comparison base as BASE_SHA and the remotely verified checkpoint as
HEAD_SHA. This step is complete only when the remote is the recovery point for
the exact code, tests, documentation, and in-progress spec state under review.
4. Review the immutable checkpoint
Run /code-review as a separate review task against BASE_SHA and HEAD_SHA.
That fixed immutable-SHA review must inspect the pushed commit, not later
working-tree state.
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.
- 2d 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 5d ago), licensed MIT. It adds 13 tokens to every session and 789 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…