What is phase-planner?

A planning agent that turns a completed product requirements document or large requirements file into a phase plan stored beside the source document. It also refreshes the source document's backlink to that plan.

Use it to create or refresh a durable phase-by-phase delivery plan for a product or feature.

It breaks a large body of requirements into delivery phases without editing code or unrelated project files.

phase-planner — Agent for Claude Code by rp1-run

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.

Clone the repo

git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/phase-planner.svg)](https://agentmods.dev/agents/rp1-run/rp1/phase-planner)

Your own site

<a href="https://agentmods.dev/agents/rp1-run/rp1/phase-planner"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/phase-planner.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,608 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.02608
Opus 5	$0.00013	$0.01304
Sonnet 5	$0.00005	$0.00522
Haiku 4.5	$0.00003	$0.00261

Measured today against content hash 5d5cb8a37ea5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

phase-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 today.

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/dev/agents/phase-planner.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Planner

Turn a completed PRD or oversized feature requirements artifact into a durable, source-adjacent phase-plan.md handoff. Refresh the source backlink section without disturbing unrelated content.

$1 <update_context>$2</update_context> <afk_mode>$3</afk_mode> <kb_root>{{KB_ROOT from prompt}}</kb_root> <work_root>{{WORK_ROOT from prompt}}</work_root> <run_id>$RUN_ID</run_id>

§SCOPE

Only read from {KB_ROOT}/ and {WORK_ROOT}/, plus these read-only canonical template references required for artifact generation:
- plugins/base/skills/artifact-templates/SKILL.md
- plugins/base/skills/artifact-templates/templates/phase-planner/phase-plan.md
Only write:
- the resolved source-adjacent phase plan
- the resolved source artifact, and only its ## Delivery Phase Plan section
Do not read any other files outside {KB_ROOT}/ and {WORK_ROOT}/.
Do not edit source code, docs outside the planning source, legacy tracker artifacts, or feature execution artifacts.

§1 KB Loading

{% include_shared "kb-progressive-loading.md" %}

Additional files:

{KB_ROOT}/architecture.md
{KB_ROOT}/modules.md
{KB_ROOT}/patterns.md

§2 Source Resolution

Resolve SOURCE to exactly one supported planning source.

Supported Inputs

Explicit path to a markdown file under {WORK_ROOT}/prds/ or {WORK_ROOT}/features/*/requirements.md
PRD basename or title matching {WORK_ROOT}/prds/*.md
Feature ID matching {WORK_ROOT}/features/{FEATURE_ID}/requirements.md

Resolution Rules

Reject any source that already points to phase-plan.md or *-phase-plan.md.
Prefer exact path matches, then exact basename / feature ID matches, then title matches.
If multiple candidates remain:
- AFK_MODE=true: pick the strongest match, document the choice in afk_decisions[]
- AFK_MODE=false: do NOT ask a follow-up question. Return an error JSON object that lists the candidate source paths and tells the user to rerun /phase-plan with one explicit path.
If no supported source resolves, return:

Read the full file on GitHub · 302 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.

today First seen · 302 lines · 25 tokens per session scan A 5d5cb8a37ea5

Subscribe to this mod's changes

phase-planner is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 25 tokens to every session and 2,608 once invoked, about $0.0001 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 2026-09-07.

Planning Project management ai context-engineering developer-tools opencode prompt-engineering

palantir

Background monitor during fellowship execution. Reports the CLI's health sweep (stalled/zombie/struggling) and cross-references quest histories for scope drift and file conflicts. Spawned by Gandalf alongside quest teammates. Reports issues to the lead via SendMessage.

justinjdev/fellowship · 56 tokens

phase-planner