plan-phase

A planning tool that turns research documents into detailed coding tasks. It focuses on describing what to change, not making or checking the changes.

In plain words
What is it for?
Use it to turn findings in a research document into implementation steps, including target files, constraints, proposed solutions, and planned tests or deployment work.
Why use it?
It removes guesswork after research is finished, so a junior developer can start coding without needing extra explanations.

Skill for Claude CodeCodex

Part of the harness-engineering plugin — 8 skills, 1 command, 1 agent shipped together

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/alchemiststudiosdotai/harness-engineering/plan-phase
Any agent
npx skills add alchemiststudiosDOTai/harness-engineering --skill plan-phase
Clone the repo
git clone --depth 1 https://github.com/alchemiststudiosDOTai/harness-engineering

Made for: Claude Code, Codex.

Or install harness-engineering, the plugin that ships this one along with the rest of its 8 skills, 1 command, 1 agent.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.01774
Opus 5 $0.00018 $0.00887
Sonnet 5 $0.00007 $0.00355
Haiku 4.5 $0.00004 $0.00177

Measured 3d ago against content hash c1c789cdcf33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-phase scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Acceptance: curl /api/users returns 401 without header, 200 with valid token
skills/plan-phase/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Phase

Overview

Generate execution-ready, coding-only implementation plans from research documents. The goal is to produce plans that any JR developer can execute immediately with zero ambiguity.

North Star Rule

If a JR developer picked this up, could they start coding immediately?

If the answer is "no" or "they'd need to ask clarifying questions," the plan is incomplete.

When to Use

  • User asks to "create a plan from research"
  • User references a research doc in .artifacts/research/
  • User wants "implementation steps" from findings
  • User asks to "break down into tasks" a researched topic

What This Skill Does NOT Do

❌ DON'T ✅ DO INSTEAD
Fix code issues Document them as tasks to fix
Verify implementations Plan verification steps
Run tests Plan what tests to write
Deploy anything Plan deployment as a task
Make code changes Document exactly what changes to make

Planning Workflow

1. Read Research Doc

Read from: .artifacts/research/<topic>.md
Extract: scope, constraints, target files, unresolved questions, proposed solutions

2. Verify Git Freshness

# Capture current state
git rev-parse HEAD          # Commit SHA
git status --short          # Working tree status

3. Generate Plan File

Save as: .artifacts/plan/YYYY-MM-DD_HH-MM-SS_<topic>.md

4. Plan Structure

---
title: "<topic> implementation plan"
link: "<topic>-plan"
type: implementation_plan
ontological_relations:
  - relates_to: [[<research-link>]]
tags: [plan, <topic>, coding]
uuid: "<uuid>"
created_at: "<ISO-8601 timestamp>"
parent_research: ".artifacts/research/<file>.md"
git_commit_at_plan: "<short_sha>"
---

## Goal

- ONE singular coding-focused outcome
- Explicitly state what is OUT of scope (ops, deploy, excessive testing)

## Scope & Assumptions

- IN scope: (technical items only)
- OUT of scope: (what we're NOT doing)
- Assumptions: (frameworks, environments, libraries)

## Deliverables

- Source code modules, functions, or APIs
- Documentation limited to developer-level notes (not user docs)

## Readiness

- Preconditions: repos, libs, data schemas, sample inputs
- What must exist before starting

## Milestones

- M1: Skeleton & architecture setup
- M2: Core logic & data flow
- M3: Feature completion & refinement
- M4: Basic test(s) & integration hooks

## Work Breakdown (Tasks)

For EACH task, specify:
- **Task ID**: T001, T002, etc.
- **Summary**: What to do (present tense, actionable)
- **Owner**: who does it
- **Estimate**: time/complexity
- **Dependencies**: other task IDs
- **Target milestone**: M1-M4
- **Acceptance test**: Exactly ONE test that proves it works
- **Files/modules touched**: List exact paths

## Risks & Mitigations

Keep technical:
- Library stability issues
- API version drift
- Schema mismatch risks
- Breaking changes in dependencies

## Test Strategy

At most ONE new test per task, only for validating main coding work.
Focus on proving correctness, not coverage.

## References

- Research doc sections
- Key code references (file:line format)

## Final Gate

- **Output summary**: plan path, milestone count, tasks ready
- **Next step**: proceed to execute-phase with the generated plan path

Read the full file on GitHub · 274 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. 3d ago First seen · 274 lines · 36 tokens per session scan A c1c789cdcf33

Subscribe to this mod's changes

plan-phase is a skill published in the GitHub repository alchemiststudiosDOTai/harness-engineering (104 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,774 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens