01-planner

01-planner is a skill for Claude Code, Codex from IncommensurableHubris/fullstack-director. It costs 201 tokens per session (3,586 once invoked), scanned A, original, MIT.

A project-planning skill that turns written requirements into an ordered build plan. It divides the work into larger groups, small end-to-end sprints, and a tracked list of requirements.

In plain words
What is it for?
Use it after project discovery to plan build order, create sprint slices, maintain the requirements-to-sprint ledger, and identify requirements that still lack a home.
Why use it?
It removes the guesswork from deciding what to build first and how requirements connect to planned work. It also keeps execution status separate from the requirements themselves.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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 skills/incommensurablehubris/fullstack-director/01-planner
Any agent
npx skills add IncommensurableHubris/fullstack-director --skill 01-planner
Clone the repo
git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

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 01-planner

README.md
[![agentmods](https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/01-planner.svg)](https://agentmods.dev/skills/incommensurablehubris/fullstack-director/01-planner)
Your own site
<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/01-planner"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/01-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,586 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 $0.00201 $0.03586
Opus 5 $0.00101 $0.01793
Sonnet 5 $0.00040 $0.00717
Haiku 4.5 $0.00020 $0.00359

Measured 6d ago against content hash acca3062ba58, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

01-planner 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 6d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (evals/check_backlog.py, evals/check_patch.py, evals/fixtures/patchable/src/digest.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/01-planner/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

01 · Planner — decompose

Turn the spec spine (docs/spec/) that discovery produced into an executable build plan: build-order epics, thin end-to-end sprint slices, and the maintained backlog ledger (REQ → epic → sprint → status). You are the bridge from "what are we building?" (the spine's declarations) to "what do we build, in what order?".

Operating principle — consume and decompose, never amend

The spine is truth you read, not text you change. Skill 01 is the framework's one pure consumer/decomposer: it is the only spec-consuming skill absent from the amendment-protocol's Reconcile list — it does not challenge, gate, or mutate declarations. Two consequences:

  • Decompose invents no scope. Every REQ you plan already exists in the spine (00 bootstrapped them). If planning reveals a genuinely missing requirement — a foundation REQ with no home — that is a Tier-3 scope finding flagged back to /00-discovery reflect, never silently added. (You own the REQ-ID allocation rulemax(registry)+1 — but allocation of new scope happens through discovery's reflect, not here.)
  • Execution status is yours alone, and it lives in the ledger. A REQ's planned/in-progress/done originates in docs/planning/backlog.md. It must never be written into the spine registry (see the two-status trap below).

The flow

Run these phases in order. The slicing craft lives in references/slicing.md — load it as phase 3 begins.

1 · READ SPINE — load the declarations

Read docs/spec/specification.md (the Constitution + the REQ registry — the authoritative ID→file map) and each docs/spec/capabilities/<domain>.md. Note each REQ's priority (MUST/SHOULD/MAY). Read docs/discovery/assumption-map.md if it exists — its top Unknown+Important bet drives risk-first sequencing in phase 3. This phase is read-only; never edit a spine file.

2 · EPICS — regroup domain → build order

The spine is organized by domain (the user's declaration). Regroup those REQs into chronological build-order epics: foundation (accounts, auth, core data model) → core workflow → consuming features. Each epic depends on the ones before it. Build order is your execution call — it is not a declaration and never goes back into the spine.

Read the full file on GitHub · 174 lines

Files

What ships with it

37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 174 lines · 201 tokens per session scan A acca3062ba58

Subscribe to this mod's changes

01-planner is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 26d ago), licensed MIT. It adds 201 tokens to every session and 3,586 once invoked, about $0.0010 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 2026-08-31.

Related

Other skills, from other repositories