plan

A planning method for large initiatives that need to be split into several connected tasks. It maps task dependencies in a directed graph and groups independent tasks into parallel waves.

In plain words
What is it for?
Use it to break an epic into smaller tasks, show which tasks depend on others, and decide which work can happen at the same time.
Why use it?
It prevents a large body of work from becoming an unclear list of tasks with hidden ordering problems. It also keeps planning separate from writing code.

Skill for Claude CodeCodex

Part of the craftlight plugin — 7 skills, 2 hooks 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/progiri/craftlight/plan
Any agent
npx skills add progiri/craftlight --skill plan
Clone the repo
git clone --depth 1 https://github.com/progiri/craftlight

Made for: Claude Code, Codex.

Or install craftlight, the plugin that ships this one along with the rest of its 7 skills, 2 hooks.

Per session 232 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,904 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.

ModelPer sessionOnce invoked
Fable 5 $0.00232 $0.02904
Opus 5 $0.00116 $0.01452
Sonnet 5 $0.00046 $0.00581
Haiku 4.5 $0.00023 $0.00290

Measured 3d ago against content hash 9ad5a68a47fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

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/craftlight/skills/plan/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

plan — decomposing an initiative into waves of tasks

Principle: plan sits ABOVE task. It takes an initiative whose scope is not one task but several, talks it through, builds a DAG of separate tasks, and lays them out into waves of parallel execution. Each DAG leaf is a future task call (which classifies the leaf as S/M/L and writes the code itself). Ceremony is proportional: you take on plan only when the initiative objectively breaks into many tasks. The planner doesn't write code and doesn't drive execution — it plans and stops.

Not for this skill: a single task, even a large, multi-file one → task (its L mode slices it into phases within a single branch); review without edits → code-review; recording decisions/gotchas as a graph → craft-graph. Realized along the way that you're facing one task, not a batch → leave and hand off to task.

Step 0. Orientation and resume

There's a CRAFT.md → read it first: the project map, the starting point. The craftlight block upsert in the root CLAUDE.md (reference and procedure — skills/task/templates/CLAUDE-block.md) rides with plan's first write to disk — the saved pre-gate draft or step 4, whichever comes first — never earlier: until then plan writes no files at all, and a call that never writes must not edit the user's CLAUDE.md.

A docs/crafts/*/PLAN.md with status draft (gate not passed, DAG empty) or in-progress (gate passed, waves running) exists:

  • The message brings a new initiative → plan it as usual; no blocking question — one FYI line in the reply: parked: plan "<initiative>" (<status>) — say "continue the plan" to get back to it.
  • A bare resume trigger ("continue the plan", "where are we in the plan") → resume by the plan's status. Several parked plans → ask which one.
  • draft → continue the discussion from the last pulse in the "Log" (the gate is still ahead). in-progress with unclosed waves → reconcile cheaply — only the first unclosed wave's leaves plus any specs marked in-progress: earlier waves are already reconciled, later ones must not have started — check off the completed leaves and show the current wave (the first one with unclosed tasks). All leaves done — no unclosed waves → the initiative is complete: offer to close the plan (status done, fill in "Outcome").
  • The plan is external memory: resuming reads the PLAN, not the chat history. Refusal → leave the plan in place; drop it only on an explicit request (status abandoned — resume won't surface it again). Resuming individual tasks (by SPEC.md) is the concern of task, not plan: plan operates on waves, task on its own specs.

Read the full file on GitHub · 139 lines

Files

What ships with it

2 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.

  1. 3d ago First seen · 139 lines · 232 tokens per session scan A 9ad5a68a47fc

Subscribe to this mod's changes

plan is a skill published in the GitHub repository progiri/craftlight (5 stars, last pushed 8d ago), licensed MIT. It adds 232 tokens to every session and 2,904 once invoked, about $0.0012 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.

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