spec-manager

spec-manager is a skill for Claude Code, Codex from KaydenClark/LLM_Workbench. It costs 22 tokens per session (1,000 once invoked), scanned A, original, MIT.

An execution-management role for one defined project specification. It dispatches and monitors workers on planned tasks, checks their returned work, combines proven results on the specification's branch, and reports the candidate onward.

In plain words
What is it for?
Use it to assign planned tasks, monitor progress, assess hand-backs, integrate completed work, and report the assembled result to a project lead.
Why use it?
It keeps task status, dependencies, blockers, and branch scope in one tracked workflow. This reduces duplicated queues and makes incomplete or unverified work visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to assign planned tasks, monitor progress, assess hand-backs, integrate completed work, and report the assembled result to a project lead.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kaydenclark/llm_workbench/spec-manager
Install

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.

Any agent
npx skills add KaydenClark/LLM_Workbench --skill spec-manager
Clone the repo
git clone --depth 1 https://github.com/KaydenClark/LLM_Workbench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for spec-manager

README.md
[![agentmods](https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/spec-manager/github.svg)](https://agentmods.dev/skills/kaydenclark/llm_workbench/spec-manager)
Your own site
<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.

agentmods 80×15 button for spec-manager

Your own site · 80×15
<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>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 11d ago against content hash 325736d60650, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

workbench/skills/spec-manager/SKILL.md · 89 lines

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.

Read the full file on GitHub · 89 lines

Changes

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.

  1. 11d ago Changed · +7 lines 325736d60650
  2. 12d ago First seen · 82 lines · 22 tokens per session scan A 0b189a547f6c

Subscribe to this mod's changes

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.