spec-orchestrator

spec-orchestrator is a command for Claude Code from zircote/subcog. It costs 42 tokens per session (9,981 once invoked), scanned A, original, MIT.

A command that coordinates the implementation of a large software specification by discovering its requirements, planning tasks, and assigning work to groups of coding agents.

In plain words
What is it for?
Use it to process a specification directory, run interactively or automatically, coordinate parallel implementation teams, and record decisions.
Why use it?
It organizes complex specification work into planned waves so dependencies and progress are easier to manage.

Command for Claude Code

Part of the subcog plugin — 4 skills, 9 commands, 5 hooks shipped together

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/zircote/subcog/spec-orchestrator
Clone the repo
git clone --depth 1 https://github.com/zircote/subcog

Made for: Claude Code.

Or install subcog, the plugin that ships this one along with the rest of its 4 skills, 9 commands, 5 hooks.

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-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/commands/zircote/subcog/spec-orchestrator.svg)](https://agentmods.dev/commands/zircote/subcog/spec-orchestrator)
Your own site
<a href="https://agentmods.dev/commands/zircote/subcog/spec-orchestrator"><img src="https://agentmods.dev/badge/commands/zircote/subcog/spec-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,981 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 $0.00042 $0.09981
Opus 5 $0.00021 $0.04991
Sonnet 5 $0.00008 $0.01996
Haiku 4.5 $0.00004 $0.00998

Measured 4d ago against content hash f501e600433d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-orchestrator 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/spec-orchestrator.md · 859 lines

How it starts

The opening of the file, as written. The whole thing — 859 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Orchestrator Command

You are now running the spec-orchestrator procedure. You will execute this step-by-step in the main conversation, keeping the user informed at every phase. Heavy work (reading specs, writing code) is delegated to Task subagents. You orchestrate the lifecycle.

Argument Parsing

Parse $ARGUMENTS for flags and the spec directory:

  • --auto: Autonomous mode. Skip all AskUserQuestion checkpoints, accept all recommendations as-is, and perform maximum work identified. Log decisions to ${WORK_DIR}/orchestrator-decisions.md instead of asking.
  • Spec directory: Any argument that is not a flag. Defaults to docs/spec/.

Examples:

  • /spec-orchestrator → interactive mode, docs/spec/
  • /spec-orchestrator docs/api-spec/ → interactive mode, docs/api-spec/
  • /spec-orchestrator --auto → autonomous mode, docs/spec/
  • /spec-orchestrator --auto docs/api-spec/ → autonomous mode, docs/api-spec/

Set AUTO_MODE=true if --auto is present, false otherwise.

Work Directory

All orchestration artifacts are stored in the mnemonic blackboard under a project-specific path. This avoids collisions when running concurrent orchestrations across multiple projects and persists data across sessions for audit and resumption.

# Derive the mnemonic blackboard path for this project
# MNEMONIC_ROOT is typically ~/.local/share/mnemonic
# The org/project path mirrors the git remote (e.g., zircote/atlatl)
MNEMONIC_ROOT="${MNEMONIC_ROOT:-$HOME/.local/share/mnemonic}"
GIT_REMOTE_PATH=$(git remote get-url origin 2>/dev/null | sed 's|.*github.com[:/]||; s|\.git$||')
WORK_DIR="${MNEMONIC_ROOT}/${GIT_REMOTE_PATH}/.blackboard/orchestrator"
mkdir -p "${WORK_DIR}/discovery"

Example paths per project:

  • atlatl~/.local/share/mnemonic/zircote/atlatl/.blackboard/orchestrator/
  • nsip~/.local/share/mnemonic/zircote/nsip/.blackboard/orchestrator/

All paths in this command reference ${WORK_DIR} — e.g., ${WORK_DIR}/discovery/, ${WORK_DIR}/task-manifest.md, ${WORK_DIR}/orchestrator-decisions.md, ${WORK_DIR}/audit-report.md.

Read the full file on GitHub · 859 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 · 859 lines · 42 tokens per session scan A f501e600433d

Subscribe to this mod's changes

spec-orchestrator is a command published in the GitHub repository zircote/subcog (28 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 9,981 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 2026-08-30.