Agent skill

Planning With Files

by jd-opensource in jd-opensource/JoySafeter

Implements Manus-style file-based planning for complex tasks.

Apache-2.0Auto-check: notesAgent Workflows

Install Planning With Files

skills CLI
$ npx skills add jd-opensource/JoySafeter --skill planning-with-files -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jd-opensource/JoySafeter planning-with-files --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jd-opensource/JoySafeter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/planning-with-files .claude/skills/planning-with-files && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
planning-with-files
GitHub stars
313
Used in
18 other repos
Token cost
~1.8k tokens
SKILL.md length
549 words
Files
11 (incl. scripts)
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

Implements Manus-style file-based planning for complex tasks.

  • Works in 6 steps: Create Plan First → The 2-Action Rule → Read Before Decide → …
  • Starting complex multi-step tasks
  • SKILL.md covers FIRST: Check for Previous…, Important: Where Files Go, Quick Start and The Core Pattern, plus 10 more sections
  • Runs PowerShell, Shell and Python scripts from its folder; calls python3 and git

What it does

Planning With Files is an agent skill from jd-opensource/JoySafeter. Implements Manus-style file-based planning for complex tasks. Creates taskplan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring 5 tool calls. Now with automatic session recovery after /clear.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts (for example `examples.md`, `reference.md` and `scripts/check-complete.sh`).

It sits in Agent Workflows, covering Planning. The repository describes itself as: 🚀 JoySafeter: An enterprise AI Agent Platform—Not just chatting. building、running、testing, and tracing autonomous Agent Teams with visual orchestration... The licence is Apache-2.0.

When your agent uses it

  • Starting complex multi-step tasks
  • Research projects
  • Any task requiring 5 tool calls

Example prompts

  • “Use the planning-with-files skill to implement Manus-style file-based planning for complex tasks”
  • “/planning-with-files”

Requirements

  • Python 3
  • A Bash shell
  • PowerShell
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Create Plan First
  2. The 2-Action Rule
  3. Read Before Decide
  4. Update After Act
  5. Log ALL Errors
  6. Never Repeat Failures

What it can do on your machine

Read from SKILL.md and the folder at commit 12234a1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Glob
    • Grep
    • WebFetch
    • WebSearch

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 5 files in scripts/ (PowerShell, Shell and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Planning With Files loads about 1.8k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 549 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from jd-opensource/JoySafeter at commit 12234a1, republished under its Apache-2.0 licence (© jd-opensource). 549 words, ~1,759 tokens.

Download SKILL.mdSave it as .claude/skills/planning-with-files/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
planning-with-files
description
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
allowed-tools
Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch
version
2.3.0
user-invocable
true

Planning with Files

Work like Manus: Use persistent markdown files as your "working memory on disk."

FIRST: Check for Previous Session (v2.2.0)

Before starting work, check for unsynced context from a previous session:

bash
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/session-catchup.py "$(pwd)"

If catchup report shows unsynced context:

  1. Run git diff --stat to see actual code changes
  2. Read current planning files
  3. Update planning files based on catchup + git diff
  4. Then proceed with task

Important: Where Files Go

  • Templates are in ${CLAUDE_PLUGIN_ROOT}/templates/
  • Your planning files go in your project directory
LocationWhat Goes There
Skill directory (${CLAUDE_PLUGIN_ROOT}/)Templates, scripts, reference docs
Your project directorytask_plan.md, findings.md, progress.md

Quick Start

Before ANY complex task:

  1. Create task_plan.md — Use templates/task_plan.md as reference
  2. Create findings.md — Use templates/findings.md as reference
  3. Create progress.md — Use templates/progress.md as reference
  4. Re-read plan before decisions — Refreshes goals in attention window
  5. Update after each phase — Mark complete, log errors

Note: Planning files go in your project root, not the skill installation folder.

The Core Pattern

Context Window = RAM (volatile, limited)
Filesystem = Disk (persistent, unlimited)

→ Anything important gets written to disk.

File Purposes

FilePurposeWhen to Update
task_plan.mdPhases, progress, decisionsAfter each phase
findings.mdResearch, discoveriesAfter ANY discovery
progress.mdSession log, test resultsThroughout session

Critical Rules

1. Create Plan First

Never start a complex task without task_plan.md. Non-negotiable.

2. The 2-Action Rule

"After every 2 view/browser/search operations, IMMEDIATELY save key findings to text files."

This prevents visual/multimodal information from being lost.

3. Read Before Decide

Before major decisions, read the plan file. This keeps goals in your attention window.

4. Update After Act

After completing any phase:

  • Mark phase status: in_progress → complete
  • Log any errors encountered
  • Note files created/modified
5. Log ALL Errors

Every error goes in the plan file. This builds knowledge and prevents repetition.

markdown
## Errors Encountered
| Error | Attempt | Resolution |
|-------|---------|------------|
| FileNotFoundError | 1 | Created default config |
| API timeout | 2 | Added retry logic |
6. Never Repeat Failures
if action_failed:
    next_action != same_action

Track what you tried. Mutate the approach.

The 3-Strike Error Protocol

ATTEMPT 1: Diagnose & Fix
  → Read error carefully
  → Identify root cause
  → Apply targeted fix

ATTEMPT 2: Alternative Approach
  → Same error? Try different method
  → Different tool? Different library?
  → NEVER repeat exact same failing action

ATTEMPT 3: Broader Rethink
  → Question assumptions
  → Search for solutions
  → Consider updating the plan

AFTER 3 FAILURES: Escalate to User
  → Explain what you tried
  → Share the specific error
  → Ask for guidance

Read vs Write Decision Matrix

SituationActionReason
Just wrote a fileDON'T readContent still in context
Viewed image/PDFWrite findings NOWMultimodal → text before lost
Browser returned dataWrite to fileScreenshots don't persist
Starting new phaseRead plan/findingsRe-orient if context stale
Error occurredRead relevant fileNeed current state to fix
Resuming after gapRead all planning filesRecover state
Show full SKILL.md (188 more words)Show less

The 5-Question Reboot Test

If you can answer these, your context management is solid:

QuestionAnswer Source
Where am I?Current phase in task_plan.md
Where am I going?Remaining phases
What's the goal?Goal statement in plan
What have I learned?findings.md
What have I done?progress.md

When to Use This Pattern

Use for:

  • Multi-step tasks (3+ steps)
  • Research tasks
  • Building/creating projects
  • Tasks spanning many tool calls
  • Anything requiring organization

Skip for:

  • Simple questions
  • Single-file edits
  • Quick lookups

Templates

Copy these templates to start:

Scripts

Helper scripts for automation:

  • scripts/init-session.sh — Initialize all planning files
  • scripts/check-complete.sh — Verify all phases complete
  • scripts/session-catchup.py — Recover context from previous session (v2.2.0)

Advanced Topics

Anti-Patterns

Don'tDo Instead
Use TodoWrite for persistenceCreate task_plan.md file
State goals once and forgetRe-read plan before decisions
Hide errors and retry silentlyLog errors to plan file
Stuff everything in contextStore large content in files
Start executing immediatelyCreate plan file FIRST
Repeat failed actionsTrack attempts, mutate approach
Create files in skill directoryCreate files in your project

© jd-opensource, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts) in skills/planning-with-files of jd-opensource/JoySafeter.

  • SKILL.md
  • examples.md
  • reference.md
  • scripts/check-complete.ps1
  • scripts/check-complete.sh
  • scripts/init-session.ps1
  • scripts/init-session.sh
  • scripts/session-catchup.py
  • templates/findings.md
  • templates/progress.md
  • templates/task_plan.md

Open the folder on GitHubat commit 12234a1

Used in 18 other repositories

We found 30 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 18 other GitHub owners. This page covers the copy in jd-opensource/JoySafeter, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Planning With Files next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Planning With Files compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Planning With Files this skilljd-opensource/JoySafeter31318 repos~1.8kAutomated safety check: NotesApache-2.0
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Interview Meaddyosmani/agent-skills102k6 repos~3.8kAutomated safety check: PassMIT
OpenSpec Guided OnboardingFission-AI/OpenSpec71k1 repos~4.5kAutomated safety check: PassMIT
Writing Plansgeeksblabla/stateofdev.ma16356 repos~661Automated safety check: PassNone
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    102k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • OpenSpec Guided Onboarding

    Fission-AI/OpenSpec

    Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.

    71k GitHub starsUsed in 1 repo~4.5k tokens
    Agent WorkflowsAuto-check passed
  • Writing Plans

    geeksblabla/stateofdev.ma

    A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…

    163 GitHub starsUsed in 56 repos~661 tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans

    geeksblabla/stateofdev.ma

    A skill your agent uses when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches…

    163 GitHub starsUsed in 40 repos~581 tokens
    Agent WorkflowsAuto-check passed

More from jd-opensource/JoySafeter

  • Openclaw Security Checker

    jd-opensource/JoySafeter

    OpenClaw 安全检测工具,基于安全实践指南验证配置安全、权限隔离、网络策略、日志审计和运行时完整性. An agent skill from jd-opensource/JoySafeter.

    313 GitHub stars~1.2k tokensUpdated 28 days ago
    Auto-check passed
  • Openclaw Threat Detect

    jd-opensource/JoySafeter

    OpenClaw 攻击模式检测工具,识别数据外传、反弹Shell、文件泄露、Prompt注入、供应链投毒等高危行为,支持 MITRE ATT&CK 映射

    313 GitHub stars~1.3k tokensUpdated 28 days ago
    Auto-check: warnings

Categories

Questions about Planning With Files

What does Planning With Files do?

Implements Manus-style file-based planning for complex tasks. Planning With Files is an agent skill from jd-opensource/JoySafeter. Implements Manus-style file-based planning for complex tasks.

When should I use Planning With Files?

Planning With Files fits situations like: starting complex multi-step tasks; research projects; any task requiring 5 tool calls.

How do I install Planning With Files in Claude Code?

Run `npx skills add jd-opensource/JoySafeter --skill planning-with-files -a claude-code`. Or copy the skill folder (skills/planning-with-files in jd-opensource/JoySafeter) into .claude/skills/planning-with-files in your project. Claude Code loads it when a task matches its description.

How do I install Planning With Files in Codex?

Run `npx skills add jd-opensource/JoySafeter --skill planning-with-files -a codex`. Or copy the skill folder (skills/planning-with-files in jd-opensource/JoySafeter) into .agents/skills/planning-with-files in your project. Codex loads it when a task matches its description.

Can I use Planning With Files in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jd-opensource/JoySafeter --skill planning-with-files -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/planning-with-files, .gemini/skills/planning-with-files, .github/skills/planning-with-files and .opencode/skills/planning-with-files in your project.

What does Planning With Files need to run?

Going by SKILL.md and its folder, Planning With Files needs PowerShell, a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3 and git). Our summary lists: Python 3; A Bash shell; PowerShell. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch.

Does Planning With Files access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Planning With Files safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Planning With Files use?

Planning With Files is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Planning With Files use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Planning With Files?

Skills that share tags, products or a category with Planning With Files: Executing Plans Inline (obra/superpowers, 296k stars), Interview Me (addyosmani/agent-skills, 102k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Planning With Files?

jd-opensource (a GitHub organization) maintains it in jd-opensource/JoySafeter, which has 313 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 9, 2026.

Source: jd-opensource/JoySafeter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.