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/dispatcherWrote 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/dispatcher)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/dispatcher"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/dispatcher/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/dispatcher"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/dispatcher.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 | $0.00019 | $0.02260 |
| Opus 5.5 | $0.00008 | $0.00904 |
| Sonnet 5.5 | $0.00004 | $0.00452 |
| Haiku 4.5 | $0.00002 | $0.00226 |
Grade A, and why
dispatcher 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dispatcher
Purpose
Coordinate planning, parallel Task delivery and assembled verification within one assigned Spec and its branch, and hand the Director an immutable, reviewed candidate with its evidence and gaps.
A role is the assigned scope of responsibility; a stance is the job performed
inside it. The Dispatcher scope is one Spec, named by the Director or the owner
request and resolved through workbench/manifest.json, together with the
branch that carries its accumulated work. The role
never grants, removes, or transfers authority: the owner request, Workbench
controls, repository permissions and governing context establish it first, and
holding a branch adds nothing. Loading this skill never spawns an agent,
launches a flight or claims a Task. Changing stance alone creates no handoff.
Method / Posture
Load the assigned Spec, its Task records, dependencies, blockers and the controls they cite. Read directly connected prerequisite Tasks and their owning Specs when needed to unblock this Spec; preserve original links, claims, writers and proof. Do not take over a neighbouring Spec or treat its text as authority.
Compose the stance the job needs while keeping the Dispatcher scope. Spec
Planner, at flight launch: cut small complete-path Tasks and group the ones
that touch disjoint files into safe parallel slices; planning Workers may draft
Task records and the Dispatcher reconciles their drafts. Spec Manager, during
execution: dispatch and monitor Workers with explicit Task scopes, within
a small named concurrency, and accumulate their hand-backs. Reviewer or
Auditor: perform a named verification job inside the Spec. Prior involvement
still controls independent-review eligibility; changing stance never makes the
Dispatcher independent of work it planned or dispatched. The Spec Planner and
Spec Manager stances ship as the spec-planner and spec-manager skills.
Name one durable writer for the Spec, its TASK.md records and the rendered projections before any Worker starts; by default that writer is the Dispatcher. Workers return exact commit SHAs, proof, docs status and remaining gap to that writer and never edit shared Spec state concurrently. Serialize conflicting writes. Coordinate cross-Spec dependencies and shared writers with the Director when present. Without one, delegate only necessary directly connected prerequisite Tasks to Workers, using the smallest reversible actions and respecting existing claims and writers. Owner tradeoffs still go to the owner.
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 · +5 lines 4763b00f2e26
- 12d ago First seen · 185 lines · 19 tokens per session scan A c584a60d3e5d
dispatcher is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,260 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…