plan

A planning workflow for software changes. It researches a codebase and writes a specification and phased implementation plan with tasks tied to specific files.

In plain words
What is it for?
Planning features, bug fixes, refactors, or maintenance work in an existing repository.
Why use it?
It reduces guesswork before coding by recording the relevant architecture, acceptance checks, dependencies, and risks.

Skill for Claude CodeCodex

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/fortunto2/rust-code/plan
Any agent
npx skills add fortunto2/rust-code --skill plan
Clone the repo
git clone --depth 1 https://github.com/fortunto2/rust-code

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 676 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 $0.00016 $0.00676
Opus 5 $0.00008 $0.00338
Sonnet 5 $0.00003 $0.00135
Haiku 4.5 $0.00002 $0.00068

Measured 2d ago against content hash bfda2d70b383, 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 2d 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.

skills/plan/SKILL.md · 66 lines

What it actually says

WORKFLOW:

  1. READ CLAUDE.md + README.md — architecture, stack, constraints
  2. TREE root level=3 — understand project structure
  3. SEARCH for keywords from task description — find affected files
  4. READ existing plans — list("docs/plan") to check overlap
  5. GENERATE track ID: {shortname}_{YYYYMMDD} (kebab-case)
  6. WRITE docs/plan/{trackId}/spec.md:
    # Specification: {Title}
    **Track ID:** {trackId}
    **Type:** Feature|Bug|Refactor|Chore
    **Created:** {date}
    ## Summary — 1-2 paragraphs from research
    ## Acceptance Criteria — 3-8 concrete checkboxes
    ## Dependencies
    ## Out of Scope
    ## Technical Notes — architecture decisions, reusable code found
    
  7. WRITE docs/plan/{trackId}/plan.md:
    # Implementation Plan: {Title}
    **Spec:** [spec.md](./spec.md)
    ## Phase 1: {Name}
    ### Tasks
    - [ ] Task 1.1: {description with file paths}
    ### Verification
    - [ ] {check}
    ## Phase N: Docs & Cleanup
    - [ ] Update CLAUDE.md
    - [ ] Remove dead code
    ## Context Handoff
    ### Key Files — from research
    ### Decisions Made — why X over Y
    ### Risks
    
  8. UPDATE_PLAN with phases as steps (pending/in_progress/completed)
  9. FINISH with: "Track {trackId}: {N} phases, {N} tasks"

RULES:

  • Every task mentions specific FILE PATHS (from research, not guessed)
  • 5-15 tasks total across 2-4 phases
  • Last phase always "Docs & Cleanup"
  • Every acceptance criterion maps to at least one task
  • Tasks are atomic — one commit each

WRONG: Plan without reading code first (guessing file paths) CORRECT: research → spec → plan → update_plan → finish

EXAMPLE — Plan a new feature: Instruction: "plan adding WebSocket support"

  1. read("CLAUDE.md") → understand architecture
  2. tree("/", 3) → find relevant modules
  3. search("/", "websocket|ws|socket") → check existing code
  4. write("docs/plan/websocket-support_20260412/spec.md", ...)
  5. write("docs/plan/websocket-support_20260412/plan.md", ...)
  6. update_plan(plan: [{step: "Phase 1: Protocol", status: "pending"}, ...])
  7. finish("Track websocket-support_20260412: 3 phases, 8 tasks")
Files

What ships with it

1 file 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. 2d ago First seen · 66 lines · 16 tokens per session scan A bfda2d70b383

Subscribe to this mod's changes

plan is a skill published in the GitHub repository fortunto2/rust-code (41 stars, last pushed 10d ago), licensed MIT. It adds 16 tokens to every session and 676 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 2026-08-30.