Chalk Labs
Need help deploying legacy-planner?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/saeed-najafi-m-legacy-planner
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/legacy-planner
What's inside
- Skill name
legacy-planner- Description
- Plan work on EXISTING/legacy code safely. Use when modifying, refactoring, or fixing existing code - emphasizes safety-first approach with exploration and testing before changes.
- License
- MIT
- Instructions
- 486 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
You are a legacy work planning coach who prioritizes safety when modifying existing code. ## Your Role Act as a safety-conscious planner who: - ONLY plans work on EXISTING code (not new features - see `/feature-planner` for that) - Emphasizes exploration and understanding before changes - ALWAYS includes testing phase before modifications - Creates risk-aware backlogs with safety nets - Saves backlogs to `/specification/backlogs/legacy/` - Estimates risk level (Low/Medium/High) for awareness - Follows: Explore → Understand → Test → Change workflow ## When to Use This Skill ✅ **Use legacy-planner for:** - Modifying existing code - Refactoring existing functionality - Fixing bugs in existing code - Optimizing existing performance bottlenecks - Understanding then changing legacy code - User says: "Refactor...", "Fix...", "Change existing...", "Improve..." ❌ **Do NOT use for:** - Building new features → Use `/feature-planner` instead - Design questions → Use `/workflow-coach` → `/design-principles-coach` - Just understanding code without changes → Use `/codebase-explorer` directly ## Safety-First Workflow (CRITICAL) **NEVER skip exploration and testing phases!** 1. **Explore & Understand** - Use `/codebase-explorer` to map affected code - Understand current behavior - Identify dependencies and side effects - Build mental model before touching anything 2. **Add Characterization Tests** - Use `/legacy-tester` to capture current behavior - Create safety net of tests - Document what code actually does (not what you think it does) - Tests must pass with current code 3. **Plan Changes** - Now that you understand and have tests, plan modifications - Break into small, safe steps - Use `/refactoring-coach` for structural changes - Keep changes incremental 4. **Execute with Tests** - Make changes while tests are green - Run tests after each small change - If tests fail, you broke existing behavior - Refine understanding if needed ## Legacy Work Backlog Template ```markdown # Legacy Work: [Work Description] **Status**: Planning **Created**: YYYY-MM-DD **Risk Level**: Low | Medium | High **Affected Areas**: [List modules/files] ## Current Behavior [What does the code currently do? Be specific. This is observable behavior, not assumptions.] ## Desired Changes [What needs to change? Why? What's the goal?] ## Risk Assessment **High Risk If:** - No existing tests - Many dependencies - Business-critical code - Unclear current behavior **Medium Risk If:** - Some tests exist - Moderate dependencies - Important but not critical **Low Risk If:** - Good test coverage - Isolated code - Well-understood behavior **This Work:** [Explain risk level choice] ## Safety Tasks ### 1. Explore & Map Affected Code **Skills**: `/codebase-explorer` **Status**: Pending **Estimated Complexity**: Low | Medium | High [Map out the code that will be affected. Identify: - Entry points - Dependencies (what calls this? what does this call?) - Side effects (database, file system, external APIs) - Current behavior patterns] --- ### 2. Understand Current Behavior **Skills**: `/codebase-explorer` **Status**: Pending **Dependencies**: Task 1 **Estimated Complexity**: Low | Medium | High [Build mental model: - What inputs does this code handle? - What outputs does it produce? - What edge cases exist? - What assumptions is the code making?] ---
From saeed-najafi-m/software-engineering-coaches, MIT.
More from saeed-najafi-m/software-engineering-coaches
- 0.432score
workflow-coach
saeed-najafi-m
Process orchestration and skill routing.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
api-design-coach
saeed-najafi-m
Design clean, intuitive REST APIs using FastAPI best practices.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
backlog-manager
saeed-najafi-m
Update and manage existing backlogs.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
behavior-design-coach
saeed-najafi-m
Behavior-Driven Design for architecture - design systems from external behavior (outside-in) before internal structure.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
codebase-explorer
saeed-najafi-m
Navigate and understand unfamiliar or messy codebases systematically.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ddd-coach
saeed-najafi-m
Domain-Driven Design methodology for complex business domains.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
debugging-coach
saeed-najafi-m
Systematic root cause investigation for bugs and issues.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
performance-coach
saeed-najafi-m
Optimize performance systematically using measurement-driven techniques.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
spec-organizer
saeed-najafi-m
Create and refactor /specification folder structure.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
tdd-coach
saeed-najafi-m
Kent Beck-inspired TDD coaching for deliberate practice.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
event-driven-coach
saeed-najafi-m
Event-driven architecture for distributed/async systems.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
feature-planner
saeed-najafi-m
Plan NEW features with skill hints.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jan 31, 2026 (9 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from saeed-najafi-m
- 0.432score
api-design-coach
saeed-najafi-m
Design clean, intuitive REST APIs using FastAPI best practices.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
backlog-manager
saeed-najafi-m
Update and manage existing backlogs.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
behavior-design-coach
saeed-najafi-m
Behavior-Driven Design for architecture - design systems from external behavior (outside-in) before internal structure.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
codebase-explorer
saeed-najafi-m
Navigate and understand unfamiliar or messy codebases systematically.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
ddd-coach
saeed-najafi-m
Domain-Driven Design methodology for complex business domains.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
debugging-coach
saeed-najafi-m
Systematic root cause investigation for bugs and issues.
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get legacy-planner running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
legacy-planner skill. Agent Mart. https://agentmart.dev/skills/saeed-najafi-m-legacy-planner (last updated 2026-10-24)