A file-backed planning skill for creating architecture plans and execution plans.

Planning a feature from a `README.md`, or breaking an existing architecture document into executable phases. It writes the plan but does not implement it.

It keeps requirements, design decisions, and implementation phases in separate documents, with evidence from the actual project and existing plans.

planner — Skill by spumer

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/spumer/i-m-senior-developer/planner

Any agent

npx skills add spumer/i-m-senior-developer --skill planner

Clone the repo

git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code, Codex.

Or install planner, the plugin that ships this one along with the rest of its 4 skills, 9 commands, 1 agent.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,117 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.

Model	Per session	Once invoked
Fable 5	$0.00050	$0.02117
Opus 5	$0.00025	$0.01059
Sonnet 5	$0.00010	$0.00423
Haiku 4.5	$0.00005	$0.00212

Measured 3d ago against content hash c9be0888a820, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (assets/execution_outputs.py, assets/plan_state.py, assets/test_execution_outputs.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.

plugins/planner/skills/planner/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner — file-backed planning

The planner produces one complete file per activation:

architecture mode writes or updates ARCHITECTURE.md;
execution mode writes or updates PLANNER_EXECUTION.md.

A successful activation never emits the full document to chat. It reports the path, kind, version, and two to four main outcomes. Full chat output is reserved for a failed write or failed metadata synchronization.

The planner writes plans; it does not execute implementation phases and does not invoke working agents.

Principles

Ready result. Architecture mode produces architecture itself, not instructions for a future architect session.
Separate roles. Requirements, architecture, and execution planning live in different files. Never write architecture and execution content to the same path.
File first. A run is successful only after the full document and its metadata are stored.
Evidence. Read the actual input and existing neighboring plans before deciding mode, version, or staleness.
Minimal change. Rewrite the current target in place. Do not create numbered history files; Git owns history.
Fail fast. Missing, unreadable, ambiguous, or colliding paths stop the run before planning.
No information loss. A stale execution plan keeps its body. A legacy PLANNER_OUTPUT.md is not deleted.

Workflow

1. Read project context

Read <project-root>/.claude/planner-context.md. If it is missing, stale, or the user explicitly requests a rescan, follow references/bootstrap.md, then return here.

The state helper is:

${CLAUDE_PLUGIN_ROOT}/skills/planner/assets/plan_state.py

Run it with python3. Do not reproduce its parsing or hashing logic in the prompt.

2. Classify the input

Feature README.md, or a feature directory containing one → architecture mode in that directory.
Existing architecture path (ARCHITECTURE.md, *-PLAN-*.md, *-DESIGN-*.md, or an explicitly supplied equivalent) → execution mode beside that file.
Free text with no readable filesystem path → architecture mode under .claude/plans/<task-slug>/.

Read the full file on GitHub · 222 lines

Files

What ships with it

10 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.

3d ago First seen · 222 lines · 50 tokens per session scan A c9be0888a820

Subscribe to this mod's changes

planner is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 2,117 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 2026-08-31.

Planning

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