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 skills add KaydenClark/LLM_Workbench --skill savegit clone --depth 1 https://github.com/KaydenClark/LLM_WorkbenchWrote 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/save)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/save"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/save/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/save"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/save.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 | $0.00042 | $0.00559 |
| Opus 5 | $0.00021 | $0.00280 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
save 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 today.
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.
What it actually says
Save
Save completed work and the context needed to continue it. This skill adds no
authority, authoring assignment, implementation loop or publication permission.
Read the current Contract and workbench/manifest.json; resolve scope and
owners before writing. Governance Planes classify a claim's use in this
operation, never its file type or storage location.
- Inventory only the work already authorized. Use
notepadfor meaningful unresolved context, corrections and the next executable action; update the current view with the revision just read. Live records remain in the manifest-declared ignored collections. Never add them to project Git. - Route supported durable truth through
to-docsto the existing owner. When selected notepad material needs promotion, composepromotewithin the same authorization. Do not create an owner, decision or assignment merely to have something to save. An ADR inworkbench/docs/adr/retains rationale and active accepted architectural decisions;canonicalized_innames their operational owners. - Check the actual changes and run their owning verification. Append named proof and remaining limitations to the assigned spec without rewriting earlier evidence. If spec state changed, render its Taskboard. Do not classify a generated view as a second authoring source.
- Follow the project's Git policy for authorized tracked changes: inspect the diff, stage only the named files, commit on the allowed task branch, and push when that recovery boundary is authorized. Verify the remote branch resolves to the intended commit. A failed or unavailable push is pending recovery, never confirmation. A save does not waive independent integration review, merge a pending review, or authorize main publication.
- Keep local context independent of optional private-session transport. If configured and within scope, use its documented save/sync procedure; report its explicit acknowledgment separately from project Git. Local bytes alone never prove remote or cross-device recovery. Transport does not move unpushed code or running processes.
If nothing changed, say so. On completion name the owners and actual local or
remote recovery points, the checks run, any pending boundary and next action.
Do not make an ordinary local save wait for optional network access. Never
copy raw working context into a tracked checkpoint. Preserve existing frozen
checkpoints and unresolved/correction/handoff dependencies; cleanup composes
notepad only after verified reconciliation.
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.
- today Changed · +1 lines 174096422986
- yesterday First seen · 45 lines · 42 tokens per session scan A 6d7ec1c5d770
save is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 559 once invoked, about $0.0002 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 2026-09-09.
Other skills, from other repositories
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.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.