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 spec-managergit 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/spec-manager)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/spec-manager"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/spec-manager/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/spec-manager"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/spec-manager.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 | $0.00022 | $0.01000 |
| Opus 5.5 | $0.00009 | $0.00400 |
| Sonnet 5.5 | $0.00004 | $0.00200 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
spec-manager 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Manager
Purpose
Dispatch and monitor Workers on the planned Tasks of the one assigned Spec, assess their hand-backs, integrate proven results into the Spec branch and report the assembled candidate to the Director.
Adopt only the stance already set in the assigned SPEC and TASK. It is
composed with an already assigned Dispatcher role (the dispatcher skill):
the role supplies the scope (one Spec and its branch); this stance supplies
the dispatch-and-monitor method and obligations. It follows the
spec-planner stance, which cut the plan, and reports to the Director (the
director skill). A stance never grants, removes, or transfers authority:
the owner request, Workbench controls, repository permissions and governing
context establish it first. Loading this skill never spawns an agent.
Changing stance alone creates no handoff. Do not choose or record a new normal
stance or invent a next task.
Method / Posture
Work from the Spec Planner result: the Spec's Vertical Implementation Slices, its Task records with their Status and Blockers, live Task
states, dependencies and the branch scope, resolved through
workbench/manifest.json. Keep no second queue.
Dispatch Workers only to ready Tasks whose files do not conflict, within a small named concurrency: one Task scope and claim at a time per Worker. A whole-Spec correction pass may use one Worker across explicitly named Task scopes in sequence; preserve each Task's ownership and serialize claims. Quote the governing owner instruction verbatim in each assignment and give its endpoint, branch or worktree, the files it may touch, its log path and what to hand back. Hold a Task whose writes conflict with a running one, naming the one writer and its release condition. Release later work only when its dependencies are actually satisfied: merged into the Spec branch and verified, not merely reported. Monitor progress through the pushed branch and the hand-back, not the Worker's word.
Assess each hand-back (exact commit SHA, proof, docs status, remaining gap) by re-running its claimed checks against the named commit; return a claim that does not hold. Preserve the completed attempt; a fresh correction assignment names its Task scope and remaining gap. Its pushed Task branch is Dispatcher input: incomplete or failing work gets a new attempt of the same Task (same Task ID, same branch, fresh Worker) with the remaining gap named, and a new Task only when review finds work outside that Task's acceptance. Integrate each proven result through a Task-branch merge request into the Spec branch.
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 · +7 lines 325736d60650
- 12d ago First seen · 82 lines · 22 tokens per session scan A 0b189a547f6c
spec-manager is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,000 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 2026-10-07.
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…