project-planning

project-planning is a skill for Claude Code from xD4O/praxis. It costs 107 tokens per session (1,038 once invoked), scanned A, original, MIT.

A project planning method for turning a goal into ordered, verifiable tasks. It accounts for dependencies, unknowns, milestones, and the riskiest work instead of producing a flat to-do list.

In plain words
What is it for?
Use it to plan features, projects, roadmaps, or build order when the work needs more than a simple task list.
Why use it?
It makes the work easier to sequence and exposes unclear tasks before implementation starts. This helps prevent work from beginning before its prerequisites exist.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the praxis plugin — 19 skills, 13 commands, 1 hook shipped together

Good fit Use it to plan features, projects, roadmaps, or build order when the work needs more than a simple task list.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xd4o/praxis/project-planning
View source ↗ xD4O/praxis
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.

Any agent
npx skills add xD4O/praxis --skill project-planning
Clone the repo
git clone --depth 1 https://github.com/xD4O/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 19 skills, 13 commands, 1 hook.

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 project-planning

README.md
[![agentmods](https://agentmods.dev/badge/skills/xd4o/praxis/project-planning/github.svg)](https://agentmods.dev/skills/xd4o/praxis/project-planning)
Your own site
<a href="https://agentmods.dev/skills/xd4o/praxis/project-planning"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/project-planning/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.

agentmods 80×15 button for project-planning

Your own site · 80×15
<a href="https://agentmods.dev/skills/xd4o/praxis/project-planning"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/project-planning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00107 $0.01038
Opus 5.5 $0.00043 $0.00415
Sonnet 5.5 $0.00021 $0.00208
Haiku 4.5 $0.00011 $0.00104

Measured 15d ago against content hash 02ac152a4c83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-planning 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 15d 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.

skills/project-planning/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Planning Protocol

EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.

A plan is not a list of things to do — it is a sequence chosen so that failure is cheap, progress is visible, and nothing starts before what it depends on exists. A flat to-do list ordered by what came to mind first is the failure this protocol prevents.

STEP 1 — Decompose into done-able tasks

Break the goal into tasks. Apply the test to EACH: "Can I write a testable done-criterion — a state someone else could confirm is reached?" ("done when a request to /login returns a session cookie"). A task you cannot write a done-criterion for is not a task yet — split it, or if it is an open question move it to an unknowns list and mark it for a spike.

STEP 2 — Make dependencies explicit

For each task, name what must already exist before it can start. This ordering is forced by the work, not by preference. A task with no stated dependency is either genuinely foundational (say so) or you have not looked hard enough (look again).

STEP 3 — Pull the riskiest task to the front

Name the single task with the most uncertainty or the highest cost-if-wrong — the one most likely to invalidate the rest of the plan. It goes FIRST, or a timeboxed spike for it does, so a wrong assumption is caught while it is cheap to fix. If your sequence puts it late, re-sequence it or state explicitly why it cannot move earlier.

STEP 4 — Group into demonstrable milestones

Group tasks into milestones. Each milestone must be a state you could SHOW someone — "a user can log in and see their orders" — never an internal-progress label like "phase 1" or "auth 50% done". A milestone with no observable deliverable is a schedule, not a plan.

STEP 5 — Report

PLAN: [goal]
├── Tasks: [task → done-criterion, one line each; unknowns flagged]
├── Dependencies: [what-blocks-what, or "foundational" where none]
├── Riskiest-first: [the task/spike sequenced first, and why it dominates]
├── Milestones: [each a demonstrable state, in order]
└── Confidence: [HIGH / MEDIUM / LOW]

Read the full file on GitHub · 87 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. 15d ago First seen · 87 lines · 107 tokens per session scan A 02ac152a4c83

Subscribe to this mod's changes

project-planning is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 1,038 once invoked, about $0.0004 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 2026-10-02.