speckit-orchestrate

speckit-orchestrate is a command for Claude Code from jmanhype/speckit. It costs 45 tokens per session (745 once invoked), scanned A, original, MIT.

A command workflow that turns a brief into a written specification, technical plan, task list, and implemented change.

In plain words
What is it for?
It helps optionally refine a brief, create Spec Kit documents, implement the planned work, and summarize the resulting files and checks.
Why use it?
It gives a software change a defined sequence from requirements through implementation, so important decisions and work items are recorded.

Command for Claude Code

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.

agentmods
npx agentmods add commands/jmanhype/speckit/speckit-orchestrate
Clone the repo
git clone --depth 1 https://github.com/jmanhype/speckit

Made for: Claude Code.

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 speckit-orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/commands/jmanhype/speckit/speckit-orchestrate.svg)](https://agentmods.dev/commands/jmanhype/speckit/speckit-orchestrate)
Your own site
<a href="https://agentmods.dev/commands/jmanhype/speckit/speckit-orchestrate"><img src="https://agentmods.dev/badge/commands/jmanhype/speckit/speckit-orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00045 $0.00745
Opus 5 $0.00023 $0.00373
Sonnet 5 $0.00009 $0.00149
Haiku 4.5 $0.00005 $0.00075

Measured 4d ago against content hash 6f9a0cb3f85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

speckit-orchestrate 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 4d 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.

.claude/commands/speckit-orchestrate.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speckit Orchestrate (Basic)

Purpose

Guide the agent to (optionally) refine the brief via TCHES' metaprompt, then run Spec Kit's passes end-to-end via SlashCommand.

Objective

Turn "$ARGUMENTS" into an executed, spec-driven change:

  1. (if --meta present and available) run TCHES' /create-meta-prompt
  2. run the Spec Kit passes: specify → plan → tasks → implement
  3. summarize artifacts, diffs, and verification status

Inputs

  • $ARGUMENTS = brief + optional flags:
    • --meta Use TCHES metaprompt to refine the brief before starting
    • --parallel Prefer parallel execution during implement where deps allow

Flow

1. Optional Meta-Prompting (if --meta flag present)

  • Check if /create-meta-prompt command exists
  • If exists and --meta flag present:
    • Run: /create-meta-prompt $ARGUMENTS
    • Use its outputs (users, outcomes, constraints) to enrich the spec phase
  • If not exists, skip and proceed to Specify

2. Specify (WHAT/WHY)

  • Run:
    • /speckit.specify $ARGUMENTS
    • (fallback if not found) /specify $ARGUMENTS
  • Keep tech decisions out of the spec

3. Plan (HOW)

  • Run:
    • /speckit.plan Draft a technical plan aligned to the spec: architecture, data model, interfaces, testing, observability, performance budgets, risks.
    • (fallback) /plan

4. Tasks (make it executable)

  • Run:
    • /speckit.tasks
    • (fallback) /tasks
  • Require small, verifiable tasks with dependencies, Definition of Done, and verification steps
  • Note: In this streamlined workflow, analyze phase is skipped. For consistency validation, use /speckit-workflow-v2 or run /speckit.analyze manually before implementation.

5. Implement (do the work)

  • Run:
    • /speckit.implement
    • (fallback) /implement
  • If --parallel present, request parallelization where dependencies allow

6. Report

  • Emit a concise summary:
    • Phases executed
    • Artifacts created/changed
    • Outstanding TODOs
    • Verification status

Notes

Read the full file on GitHub · 86 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. 4d ago First seen · 86 lines · 45 tokens per session scan A 6f9a0cb3f85e

Subscribe to this mod's changes

speckit-orchestrate is a command published in the GitHub repository jmanhype/speckit (26 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 745 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 2026-09-01.