File-Based Task Planner

Planning with files

by davila7 · MIT license · ★ 32,299 on GitHub · v2.1.2

Planning with files cover

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md.

---
name: planning-with-files
version: "2.1.2"
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.
user-invocable: true
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep
  - WebFetch
  - WebSearch
hooks:
  SessionStart:
    - hooks:
        - type: command

Overview

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

Manual install (npx, ZIP)
Claude Codenpx skills add davila7/claude-code-templates --skill planning-with-files -g -a claude-code
Claude Code (degit)npx degit davila7/claude-code-templates/cli-tool/components/skills/productivity/planning-with-files#main ~/.claude/skills/planning-with-files
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md6.5 KB
Read SKILL.md here
davila7/main1 file shown
SKILL.md
Show the full text212 lines

Planning with Files

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

Important: Where Files Go

When using this skill:

  • Templates are stored in the skill directory at ${CLAUDE_PLUGIN_ROOT}/templates/
  • Your planning files (task_plan.md, findings.md, progress.md) should be created in your project directory — the folder where you're working
Location What Goes There
Skill directory (${CLAUDE_PLUGIN_ROOT}/) Templates, scripts, reference docs
Your project directory task_plan.md, findings.md, progress.md

This ensures your planning files live alongside your code, not buried in the skill installation folder.

Quick Start

Before ANY complex task:

  1. Create task_plan.md in your project — Use templates/task_plan.md as reference
  2. Create findings.md in your project — Use templates/findings.md as reference
  3. Create progress.md in your project — 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: All three planning files should be created in your current working directory (your project root), not in the skill's installation folder.

The Core Pattern

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

→ Anything important gets written to disk.

File Purposes

File Purpose When to Update
task_plan.md Phases, progress, decisions After each phase
findings.md Research, discoveries After ANY discovery
progress.md Session log, test results Throughout 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.

## 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

Situation Action Reason
Just wrote a file DON'T read Content still in context
Viewed image/PDF Write findings NOW Multimodal → text before lost
Browser returned data Write to file Screenshots don't persist
Starting new phase Read plan/findings Re-orient if context stale
Error occurred Read relevant file Need current state to fix
Resuming after gap Read all planning files Recover state

The 5-Question Reboot Test

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

Question Answer 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

Advanced Topics

Anti-Patterns

Don't Do Instead
Use TodoWrite for persistence Create task_plan.md file
State goals once and forget Re-read plan before decisions
Hide errors and retry silently Log errors to plan file
Stuff everything in context Store large content in files
Start executing immediately Create plan file FIRST
Repeat failed actions Track attempts, mutate approach
Create files in skill directory Create files in your project
1---
2name: planning-with-files
3version: "2.1.2"
4description: 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.
5user-invocable: true
6allowed-tools:
7 - Read
8 - Write
9 - Edit
10 - Bash
11 - Glob
12 - Grep
13 - WebFetch
14 - WebSearch
15hooks:
16 SessionStart:
17 - hooks:
18 - type: command
19 command: "echo '[planning-with-files] Ready. Auto-activates for complex tasks, or invoke manually with /planning-with-files'"
20 PreToolUse:
21 - matcher: "Write|Edit|Bash"
22 hooks:
23 - type: command
24 command: "cat task_plan.md 2>/dev/null | head -30 || true"
25 PostToolUse:
26 - matcher: "Write|Edit"
27 hooks:
28 - type: command
29 command: "echo '[planning-with-files] File updated. If this completes a phase, update task_plan.md status.'"
30 Stop:
31 - hooks:
32 - type: command
33 command: "${CLAUDE_PLUGIN_ROOT}/scripts/check-complete.sh"
34---
35 
36# Planning with Files
37 
38Work like Manus: Use persistent markdown files as your "working memory on disk."
39 
40## Important: Where Files Go
41 
42When using this skill:
43 
44- **Templates** are stored in the skill directory at `${CLAUDE_PLUGIN_ROOT}/templates/`
45- **Your planning files** (`task_plan.md`, `findings.md`, `progress.md`) should be created in **your project directory** — the folder where you're working
46 
47| Location | What Goes There |
48|----------|-----------------|
49| Skill directory (`${CLAUDE_PLUGIN_ROOT}/`) | Templates, scripts, reference docs |
50| Your project directory | `task_plan.md`, `findings.md`, `progress.md` |
51 
52This ensures your planning files live alongside your code, not buried in the skill installation folder.
53 
54## Quick Start
55 
56Before ANY complex task:
57 
581. **Create `task_plan.md`** in your project — Use [templates/task_plan.md](templates/task_plan.md) as reference
592. **Create `findings.md`** in your project — Use [templates/findings.md](templates/findings.md) as reference
603. **Create `progress.md`** in your project — Use [templates/progress.md](templates/progress.md) as reference
614. **Re-read plan before decisions** — Refreshes goals in attention window
625. **Update after each phase** — Mark complete, log errors
63 
64> **Note:** All three planning files should be created in your current working directory (your project root), not in the skill's installation folder.
65 
66## The Core Pattern
67 
68```
69Context Window = RAM (volatile, limited)
70Filesystem = Disk (persistent, unlimited)
71 
72→ Anything important gets written to disk.
73```
74 
75## File Purposes
76 
77| File | Purpose | When to Update |
78|------|---------|----------------|
79| `task_plan.md` | Phases, progress, decisions | After each phase |
80| `findings.md` | Research, discoveries | After ANY discovery |
81| `progress.md` | Session log, test results | Throughout session |
82 
83## Critical Rules
84 
85### 1. Create Plan First
86Never start a complex task without `task_plan.md`. Non-negotiable.
87 
88### 2. The 2-Action Rule
89> "After every 2 view/browser/search operations, IMMEDIATELY save key findings to text files."
90 
91This prevents visual/multimodal information from being lost.
92 
93### 3. Read Before Decide
94Before major decisions, read the plan file. This keeps goals in your attention window.
95 
96### 4. Update After Act
97After completing any phase:
98- Mark phase status: `in_progress` → `complete`
99- Log any errors encountered
100- Note files created/modified
101 
102### 5. Log ALL Errors
103Every error goes in the plan file. This builds knowledge and prevents repetition.
104 
105```markdown
106## Errors Encountered
107| Error | Attempt | Resolution |
108|-------|---------|------------|
109| FileNotFoundError | 1 | Created default config |
110| API timeout | 2 | Added retry logic |
111```
112 
113### 6. Never Repeat Failures
114```
115if action_failed:
116 next_action != same_action
117```
118Track what you tried. Mutate the approach.
119 
120## The 3-Strike Error Protocol
121 
122```
123ATTEMPT 1: Diagnose & Fix
124 → Read error carefully
125 → Identify root cause
126 → Apply targeted fix
127 
128ATTEMPT 2: Alternative Approach
129 → Same error? Try different method
130 → Different tool? Different library?
131 → NEVER repeat exact same failing action
132 
133ATTEMPT 3: Broader Rethink
134 → Question assumptions
135 → Search for solutions
136 → Consider updating the plan
137 
138AFTER 3 FAILURES: Escalate to User
139 → Explain what you tried
140 → Share the specific error
141 → Ask for guidance
142```
143 
144## Read vs Write Decision Matrix
145 
146| Situation | Action | Reason |
147|-----------|--------|--------|
148| Just wrote a file | DON'T read | Content still in context |
149| Viewed image/PDF | Write findings NOW | Multimodal → text before lost |
150| Browser returned data | Write to file | Screenshots don't persist |
151| Starting new phase | Read plan/findings | Re-orient if context stale |
152| Error occurred | Read relevant file | Need current state to fix |
153| Resuming after gap | Read all planning files | Recover state |
154 
155## The 5-Question Reboot Test
156 
157If you can answer these, your context management is solid:
158 
159| Question | Answer Source |
160|----------|---------------|
161| Where am I? | Current phase in task_plan.md |
162| Where am I going? | Remaining phases |
163| What's the goal? | Goal statement in plan |
164| What have I learned? | findings.md |
165| What have I done? | progress.md |
166 
167## When to Use This Pattern
168 
169**Use for:**
170- Multi-step tasks (3+ steps)
171- Research tasks
172- Building/creating projects
173- Tasks spanning many tool calls
174- Anything requiring organization
175 
176**Skip for:**
177- Simple questions
178- Single-file edits
179- Quick lookups
180 
181## Templates
182 
183Copy these templates to start:
184 
185- [templates/task_plan.md](templates/task_plan.md) — Phase tracking
186- [templates/findings.md](templates/findings.md) — Research storage
187- [templates/progress.md](templates/progress.md) — Session logging
188 
189## Scripts
190 
191Helper scripts for automation:
192 
193- `scripts/init-session.sh` — Initialize all planning files
194- `scripts/check-complete.sh` — Verify all phases complete
195 
196## Advanced Topics
197 
198- **Manus Principles:** See [reference.md](reference.md)
199- **Real Examples:** See [examples.md](examples.md)
200 
201## Anti-Patterns
202 
203| Don't | Do Instead |
204|-------|------------|
205| Use TodoWrite for persistence | Create task_plan.md file |
206| State goals once and forget | Re-read plan before decisions |
207| Hide errors and retry silently | Log errors to plan file |
208| Stuff everything in context | Store large content in files |
209| Start executing immediately | Create plan file FIRST |
210| Repeat failed actions | Track attempts, mutate approach |
211| Create files in skill directory | Create files in your project |
212 
View all files on GitHub →

Details

Version
2.1.2
License
MIT
Stars on the repo
★ 32,299
Checked
Source
davila7/claude-code-templates ↗
Creator
davila7 · 212 listings
View creator

Similar skills

See all →
AgentPhase 2: Foundation Scaffoldingmsitarzewski/agency-agents · by msitarzewski> Duration: 3-5 days | Agents: 6 | Gate Keepers: DevOps Automator + Evidence Collector★ 154k GitHub starsAgentNEXUS Network Frameworkmsitarzewski/agency-agents · by msitarzewski> NEXUS transforms The Agency's independent AI specialists into a synchronized intelligence network. This is not a prompt collection — it…★ 154k GitHub starsSkillAnsoff Matrix Generatorphuryn/pm-skills · by phurynGenerate an Ansoff Matrix analysis mapping growth strategies across market penetration, market development, product development, and diversification. Use when considering growth options, planning market expansion, or evaluating strategic growth paths.★ 26.6k GitHub starsSkillArchitecture Advisorshadcn/improve · by shadcnSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.★ 9.2k GitHub starsSkillCareer Skills TranslatorParamchoudhary/ResumeSkills · by ParamchoudharyTranslate skills from one industry to another, identify transferable skills★ 2.4k GitHub starsSkillMarketing Skills CollectionLeoYeAI/openclaw-marketing-skills · by LeoYeAIA collection of 37 battle-tested marketing skills for OpenClaw agents. Use when you want to install or reference any marketing skill including: CRO (page-cro, signup-flow-cro, onboarding-cro, form-cro, popup-cro, paywall-upgrade-cro), copywriting, copy-editing, cold-email, email-sequence, social-content, seo-audit, ai-seo, programmatic-seo, site-architecture, schema-markup, content-strategy, paid-ads, ad-creative, ab-test-setup, analytics-tracking, referral-program, free-tool-strategy, churn-prevention, revops, sales-enablement, launch-strategy, pricing-strategy, competitor-alternatives, marketing-ideas, marketing-psychology, lead-magnets, product-marketing-context, and data connectors (google-ads-connect, search-console-connect, meta-ads-connect, x-twitter-connect). Start with product-marketing-context to set up your product context document, then use any other skill naturally. Powered by MyClaw.ai.★ 1k GitHub stars

More from davila7

Skill2D Game Developmentdavila7/claude-code-templates · by davila72D game development principles. Sprites, tilemaps, physics, camera.★ 32.3k GitHub starsSkill3D Game Development Principlesdavila7/claude-code-templates · by davila73D game development principles. Rendering, shaders, physics, cameras.★ 32.3k GitHub starsSkill3D Web Experience Builderdavila7/claude-code-templates · by davila7Expert in building 3D experiences for the web - Three.js, React Three Fiber, Spline, WebGL, and interactive 3D scenes. Covers product configurators, 3D portfolios, immersive websites, and bringing depth to web experiences. Use when: 3D website, three.js, WebGL, react three fiber, 3D experience.★ 32.3k GitHub starsSkillSplit Test Setupdavila7/claude-code-templates · by davila7When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," or "hypothesis." For tracking implementation, see analytics-tracking.★ 32.3k GitHub starsAgentResearch Literature Synthesizerdavila7/claude-code-templates · by davila7Academic research synthesis specialist. Use PROACTIVELY for comprehensive research on academic topics, literature reviews, technical investigations, and well-cited analysis combining multiple sources. <example>Context: A podcast episode needs a segment grounded in peer-reviewed evidence with formal citations. user: "Research the current state of transformer efficiency techniques for the episode, with proper academic citations." assistant: "I'll use the academic-research-synthesizer agent to search arXiv and Semantic Scholar, extract full-text findings via WebFetch, and produce a cited literature synthesis with confidence levels." <commentary>Use academic-research-synthesizer (not comprehensive-researcher) when the episode segment needs peer-reviewed sourcing, formal citation format, and explicit confidence tagging rather than general-purpose multi-source coverage.</commentary></example> <example>Context: The episode-orchestrator has routed a "literature review" request for a technical deep-dive segment. user: "Summarize the research landscape on federated learning privacy guarantees." assistant: "I'll invoke academic-research-synthesizer to systematically search academic sources, note peer-review status per source, and synthesize consensus vs. open debates."</example>★ 32.3k GitHub starsAgentAcademic Research Specialistdavila7/claude-code-templates · by davila7Academic research specialist for scholarly sources, peer-reviewed papers, and academic literature. Use PROACTIVELY for research paper analysis, literature reviews, citation tracking, and academic methodology evaluation. <example>Context: The research-orchestrator has kicked off Phase 4 parallel research on 'efficacy of intermittent fasting' and needs peer-reviewed evidence. user: "Find the academic evidence on intermittent fasting outcomes." assistant: "I'll use the academic-researcher agent to search Semantic Scholar, PubMed, and OpenAlex for peer-reviewed studies and write structured findings to academic-research.md." <commentary>The request is specifically for scholarly/peer-reviewed evidence rather than general web coverage or code, so academic-researcher (not web-researcher or technical-researcher) is the right specialist.</commentary></example> <example>Context: The user wants a literature review comparing methodologies across studies on a topic. user: "Can you review the literature on transformer model interpretability and identify research gaps?" assistant: "Let me invoke the academic-researcher agent to pull foundational and recent papers, extract methodologies, and surface open research gaps." <commentary>Literature review, methodology extraction, and research-gap identification are core academic-researcher capabilities, distinct from technical-researcher's focus on code repositories and implementations.</commentary></example>★ 32.3k GitHub stars