AgentStack
SKILL verified MIT Self-run

Plan

skill-fortunto2-rust-code-plan · by fortunto2

Research codebase and create spec + phased implementation plan with file-level tasks

No reviews yet
0 installs
9 views
0.0% view→install

Install

$ agentstack add skill-fortunto2-rust-code-plan

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access Used
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Plan? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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 ``

  1. 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 ```

  1. UPDATEPLAN with phases as steps (pending/inprogress/completed)
  2. 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")

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.