Home / levnas / ccmemo · skills/plan-task/SKILL.md · GitHub

plan-task skillA

plan-task is agent-read markdown (skill) from levnas/ccmemo: Persist multi-step plans and task progress across Claude Code sessions. Use when starting work that may span multiple sessions, resuming incomplete plans, or updating task progress. Supports two modes: Git-tracked (shared via commits) and Issue-centric (issue tracker as primary source of truth, local scratchpad for sessions)..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Plan & Task Persistence

## Goal

Maintain plans and task progress across Claude Code sessions so that work can be resumed without losing context.

## Execution

Delegate the plan/task work to a Sonnet subagent to minimize main context consumption.

1. Determine the operation mode from user input or session context
2. Prepare structured input fields for the subagent
3. Spawn a subagent with the following configuration:

```
Agent(
  subagent_type: "general-purpose",
  model: "sonnet",
  description: "plan and task management",
  prompt: |
    You are a plan and task management agent. Read the procedure file and follow it precisely.

    ## Operation
    {mode}

    ## Input
    ### what(事実)
    {what}

    ### why(判断理由)
    {why}

    ### context(背景情報)
    {context}

    ### tags_hint(推奨タグ)
    {tags_hint}

    ## Instructions
    1. Read the procedure file at: {plugin_root}/skills/plan-task/procedure.md
    2. Execute the procedure section matching the operation mode: {mode}
    3. The project root is: {project_root}
    4. The tasks directory is: {project_root}/.claude/tasks/
    5. For setup, asset files are at: {plugin_root}/skills/plan-task/assets/
…

Read the whole file at its exact version.

How to install

Latest version
mdr add levnas/ccmemo/plan-task@git:20260405.465b784
Exact content
mdr add levnas/ccmemo/plan-task@sha256:5421fee5dce6c07e

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_eq7qfl6juqjvf7kh.svg)](https://markdownregistry.com/a/art_eq7qfl6juqjvf7kh)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260405.465b784 latest2026-04-05 465b784 3,541 BA view · diff
git:20260331.02c96cb2026-03-31 02c96cb 13,569 BA view · diff
git:20260328.77c61542026-03-28 77c6154 11,439 BA view · diff
git:20260328.a1c860d2026-03-28 a1c860d 10,984 BA view · diff
git:20260316.8ba67842026-03-16 8ba6784 7,110 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3541 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

levnas/ccmemo · 4 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_eq7qfl6juqjvf7kh
GET https://markdownregistry.com/api/v1/resolve?ref=levnas/ccmemo/plan-task
GET https://markdownregistry.com/api/v1/blob/5421fee5dce6c07e6f46eb1211890e4f2b14a0bd24ad15872b72a232f917283f

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from levnas/ccmemo

recall-knowledge skill
levnas/ccmemo · skills/recall-knowledge/SKILL.md · Recall knowledge base entries by meaning, not just keywords — hybrid search (lexical ripgrep + local vector embeddings…
git:20260923.33efe69 · audit A · 4 stars
record-knowledge skill
levnas/ccmemo · skills/record-knowledge/SKILL.md · Record tacit knowledge — quirks, pitfalls, dependencies, decisions, root causes — as tagged Markdown entries in…
git:20260416.a4537a9 · audit A · 4 stars
review-knowledge skill
levnas/ccmemo · skills/review-knowledge/SKILL.md · Review and maintain the knowledge base — find stale entries, orphan entries without connections, missing links between…
git:20260726.7717424 · audit A · 4 stars
CLAUDE.md@templates/knowledge claude
levnas/ccmemo · templates/knowledge/CLAUDE.md
git:20260923.d5ee9c3 · audit A · 4 stars
CLAUDE.md@templates/tasks claude
levnas/ccmemo · templates/tasks/CLAUDE.md
git:20260310.b04ad63 · audit A · 4 stars

Every file in levnas/ccmemo

Other files named plan-task

plan-task skill
etr/groundwork · skills/plan-task/SKILL.md · Plans a task or feature - loads context, optionally clarifies requirements, spawns Plan agent, persists plan to the…
git:20260912.f731445 · audit A · 42 stars
plan-task skill
this-hw/claude-code-kit · plugins/common/skills/plan-task/SKILL.md · Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown…
git:20260907.0eeeffb · audit A · 4 stars

Browse by kind, by grade A, or by owner.