pibun: Skill for Claude Code

.agents/skills/phased-plan/SKILL.md

phased-plan is a skill for Claude Code, Codex from khairold/pibun. It costs 55 tokens per session (1,676 once invoked), scanned A, original, MIT.

A skill for turning a project specification into a phased build plan stored in a .plan directory. The plan includes progress memory, drift tracking, and session logs for work spread across multiple sessions.

In plain words
What is it for?
Use it when starting a multi-session project that needs ordered phases, clear completion checks, and shared progress notes.
Why use it?
It breaks a large project into smaller testable stages and preserves context between development sessions.

Skill for Claude CodeCodex

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

This is khairold/pibun's own configuration. It tells Claude Code and Codex how to work on pibun itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pibun configures →

Reuse

Borrowing it

Nothing to install: this file belongs to khairold/pibun. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/khairold/pibun/main/.agents/skills/phased-plan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/khairold/pibun

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 phased-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/khairold/pibun/phased-plan.svg)](https://agentmods.dev/skills/khairold/pibun/phased-plan)
Your own site
<a href="https://agentmods.dev/skills/khairold/pibun/phased-plan"><img src="https://agentmods.dev/badge/skills/khairold/pibun/phased-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,676 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 $0.00055 $0.01676
Opus 5 $0.00028 $0.00838
Sonnet 5 $0.00011 $0.00335
Haiku 4.5 $0.00006 $0.00168

Measured 7d ago against content hash fedb3d13a338, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

phased-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 7d 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.

.agents/skills/phased-plan/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phased Plan

Create a phased build plan from a project specification. This skill establishes a file system convention for managing multi-session builds with shared memory and context continuity.

When to Use

  • A project spec exists but needs to be broken into buildable phases
  • Work will span multiple sessions and needs context continuity
  • You need to prevent context rot across sessions

Process

1. Read the Spec

Read the project specification file (usually SPEC.md, docs/, or similar) and understand the full scope.

Also read existing project context if present:

  • CLAUDE.md — project identity and conventions
  • .pi/AGENTS.md — agent capabilities and playbooks
  • .agents/CONVENTIONS.md — build rules and patterns

2. Decompose into Phases

Break the spec into 3-8 phases following these rules:

  • Each phase is self-contained and testable — it delivers working functionality
  • Each phase builds on the previous — no forward dependencies
  • Each phase is completable in 1-3 sessions — if too large, split further
  • Each phase has clear exit criteria — how do you know it's done?
  • Order by dependency first, then value

Sub-phases (e.g., 1A, 1B, 1C) are useful when a major phase has distinct sub-deliverables that should be reviewed independently. Use when:

  • A phase has 15+ items that naturally group into 2-3 sub-deliverables
  • You want autopilot to pause between sub-deliverables for review
  • Different sub-phases need different expertise or context

3. Create .plan/ Directory

Create the following files:

.plan/PLAN.md — Master Plan
# {Project Name} — Build Plan

> **Spec:** {path to spec or description}
> **Status:** Not Started
> **Current Phase:** —
> **Last Session:** —

---

## Session Protocol

### At the START of every session:
1. Read `.plan/PLAN.md` (this file) — know where we are
2. Read `.plan/MEMORY.md` — absorb shared context and decisions
3. Read `.plan/DRIFT.md` — check for spec changes
4. Read `.agents/CONVENTIONS.md` — build patterns (if exists)
5. Identify the next uncompleted phase/item
6. State what you will do this session before starting

### At the END of every session:
1. Update item checkboxes in this file
2. Update `MEMORY.md` with anything the next session needs to know
3. Update `DRIFT.md` if any spec changes occurred
4. Log the session in `SESSION-LOG.md`
5. Write a **Handoff** note at the bottom of the session log entry
6. Run the build gate command (when applicable)

---

## Phase N — {Name}

**Goal:** {One sentence describing what this phase delivers}

- [ ] N.1 — {Item description}
- [ ] N.2 — {Item description}
- ...

**Exit criteria:** {How you know this phase is done}

---

## Parking Lot

Items discussed but deferred.

- [ ] {Future item}

Read the full file on GitHub · 231 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. 7d ago First seen · 231 lines · 55 tokens per session scan A fedb3d13a338

Subscribe to this mod's changes

phased-plan is a skill published in the GitHub repository khairold/pibun (19 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,676 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens