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/promoteWrote 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/promote)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/promote"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/promote/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/promote"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/promote.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 | $0.00043 | $0.00691 |
| Opus 5 | $0.00022 | $0.00345 |
| Sonnet 5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
promote 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
Promote
Promote only selected material whose authority and evidence already exist.
This primitive works with grilling decisions or other objective notepads;
make-it-so can compose it before implementation. It does not start an
interview, implement tickets, grant permission or infer invocation from a
passing mention. Read the Contract, manifest and assigned owner first.
- Resolve the named source and exact selection. Read its compact current
view, selected entries and all corrections/dependencies using
notepad. Follow pagination and inspect related rulings that could supersede it. A locked label is neither proof nor authority. Preserve open, tentative, withdrawn and superseded status; promote only the supported current claim under existing authorization. If ordering is unclear, preserve the source and report the ambiguity rather than choose a convenient interpretation. - Use
to-docsto choose the existing durable owner. Requirements and proof belong to the assigned spec, operating rules to their owning control, durable knowledge to the manifest Wiki. Decision rationale belongs inworkbench/docs/adr/, with active accepted decision claims as architectural Canon andcanonicalized_innaming operational owners. Create a needed owner only through its authorized normal workflow. File type and location do not assign a Governance Plane or grant scope. - Author a separate, ignored Markdown draft inside the project containing the complete proposed owner bytes. Distill the supported result faithfully; never copy the notepad wholesale or cite an ignored note as durable proof. Preserve existing unrelated owner content, source anchors and append-only evidence. Read the destination bytes and compute their SHA-256.
- Use the project's installed public seam, with the source revision just read:
node workbench/tools/sessions.mjs promote --from NOTE --revision N \
--entries finding-001,correction-001 --to OWNER.md --expected SHA256 \
--content AUTHORED_DRAFT.md
The Runbook owns flags, privacy/path checks, owner validation and recovery. The command returns the expanded selection and hashes; verify actual owner read-back and run its normal checks. Tool success does not prove semantic fidelity. A blocked, partial or recovery-residue result preserves the source; inspect the named recovery material before any retry or cleanup. One writer per note and owner is required; revision/hash checks are not concurrent locks.
- Record the result in the proper owner and update the note append-only,
naming the durable destination. Keep unresolved work and correction or
transfer dependencies. Use the
notepadtrim/delete public seam only once that material is reconciled and no retained context still needs it. Existing frozen checkpoints remain unchanged; no routine archive or copy is created. - Compose
savefor the achieved changes under the same scope. Pass the already-promoted result so save does not promote it again. Report the destination, verified selection and hashes, checks, remaining source context and actual recovery boundary. Stop after promotion/persistence unless the caller already authorized further work.
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 85a75ca32df2
- yesterday First seen · 57 lines · 43 tokens per session scan A c829770ebf65
promote is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 691 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.