specmanager-plan

A command that creates a phased implementation plan and task records for a SpecManager feature after checking its project documents and approval status.

In plain words
What is it for?
Use it to turn an approved feature into ordered phases and small, scored tasks for implementation.
Why use it?
It prevents planning from starting with missing approvals or duplicate draft plans, and keeps the work connected to the feature's existing documents.

Command

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/joanseg/specmanager/specmanager-plan
Clone the repo
git clone --depth 1 https://github.com/joanseg/specmanager
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 691 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 $0.00032 $0.00691
Opus 5 $0.00016 $0.00345
Sonnet 5 $0.00006 $0.00138
Haiku 4.5 $0.00003 $0.00069

Measured 2d ago against content hash 85f8b2215ee2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

specmanager-plan 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 2d 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.

plugins/specmanager/commands/specmanager-plan.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate a Plan + phased tasks for the feature: $ARGUMENTS.

Steps

  1. Resolve the feature. list_features → match by id/slug. Stop if not found.

  2. Check the gate. check_gate({ featureId, stage: "plan" }) — Architecture must be approved AND (no design doc exists OR design approved). If closed, report reason to the user (the reason string says which leg of the compound gate failed) and stop. A common case: design doc is in draft — the user either approves it or deletes the brief to skip design entirely.

  3. Confirm no draft already exists. list_documents({ featureId, stage: "plan" }). Don't duplicate.

  4. Look up the design doc id (optional). list_documents({ featureId, stage: "design" }). If a doc exists (it must be approved at this point — the gate enforced it), grab its id + version. If none exists, pass null in the subagent prompt.

  5. Invoke the subagent. Task({ subagent_type: "planner", prompt: ... }). Include:

    • Feature id, title, slug.
    • The Architecture doc id (look up first, pass explicitly).
    • The PRD doc id (for context).
    • The Design doc id + version (or null), so the planner's design-grounding step can read it.
    • Any extra context the user gave.

    The planner writes plan.md (organised into ## Phase <name> — <theme> sections with **Exit test:** lines) AND emits a create_task call per Build-order item with phase and Fibonacci complexity (≤3). Most features come back as a single named phase — that is the expected common output, not a degenerate case. The planner only splits into multiple phases for a genuinely large project with a real mid-build test boundary, and confirms any such split with you via AskUserQuestion before persisting tasks. When a design doc was passed in, the planner references the brief's screens/components/tokens by name in the plan body.

  6. Sync CLAUDE.md. Call sync_claude_md.

  7. Report. Plan doc id + file path + per-phase task counts (e.g. Phase A: 5 tasks, Phase B: 7 tasks) and whether the plan was grounded in a design brief. Suggest opening the board to see the Build column populated.

Read the full file on GitHub · 29 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. 2d ago First seen · 29 lines · 32 tokens per session scan A 85f8b2215ee2

Subscribe to this mod's changes

specmanager-plan is a command published in the GitHub repository joanseg/specmanager (19 stars, last pushed 18d ago), licensed MIT. It adds 32 tokens to every session and 691 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.