planner
Turn rough backlog issues into structured, conflict-aware task specs before anything is dispatched.
Skill by Atul-Chahar
Chalk Labs
Need help deploying 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/atul-chahar-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: productivity
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/planner
What's inside
- Skill name
planner- Description
- Turn rough backlog issues into structured, conflict-aware task specs before anything is dispatched.
- License
- MIT
- Instructions
- 22 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
You are the planner. Every dispatch depends on the spec you produce: a one-line issue sprayed across a parallel swarm produces parallel garbage. Your job is to make each task unambiguous, verifiable, and isolated. Rules: 1. Extract the real deliverable from the issue. If the issue is vague, choose the smallest interpretation that satisfies its title and write the interpretation into the acceptance criteria. 2. Acceptance criteria must be checkable by running the test command — no "works correctly", only "GET /todos?q= returns filtered results". 3. List every file the task should modify under `touches`. Two tasks that share a file in `touches` will never run concurrently; this is the main defense against merge chaos, so be precise. 4. Put files worth reading (but not modifying) under `context_files`. 5. Escalate to T2 anything that mentions merging to main, force-push, deletion, or destructive migration — before any agent sees the spec. 6. Flag specs that overlap with tasks already planned (`conflicts_with`). 7. Keep specs small. One narrow job done end to end beats a broad one done approximately.
From Atul-Chahar/Foreman, MIT.
More from Atul-Chahar/Foreman
- 0.529score
qodo-get-rules
Atul-Chahar
Loads coding rules from Qodo most relevant to the current coding task by generating a semantic search query from the assignment.
SkillBFreshness: BClaude Code +9 - 0.518score
reviewer
Atul-Chahar
Review every swarm diff before a human sees it — security checklist first, spec fidelity second.
SkillBFreshness: BClaude Code +9 - 0.518score
security-review
Atul-Chahar
A precision-first checklist applied to every diff — secrets, dynamic execution, injection, deserialization, authz.
SkillBFreshness: BClaude Code +9 - 0.518score
implementer
Atul-Chahar
Implement exactly one task spec — minimal diff, tests first, stay inside the declared scope.
SkillBFreshness: BClaude Code +9 - 0.516score
context-budget
Atul-Chahar
Token discipline for subagents — ask for listed context only, summarize instead of dumping, never request the repo tree.
SkillBFreshness: BClaude Code +9 - 0.513score
tdd-workflow
Atul-Chahar
Red, green, refactor — the failing test comes first and the spec's test command is the arbiter.
SkillBFreshness: BClaude Code +9 - 0.513score
build-fix
Atul-Chahar
Diagnose from the failing output, isolate, apply the minimal fix, re-run — never widen the blast radius.
SkillBFreshness: BClaude Code +9 - 0.513score
reconciler
Atul-Chahar
Watch the health of main, dispatch bounded fix agents when the build breaks, escalate instead of looping.
SkillBFreshness: BClaude Code +9 - 0.513score
search-first
Atul-Chahar
Read what exists before writing anything new — extend, don't duplicate.
SkillBFreshness: BClaude Code +9 - 0.499score
qodo-pr-resolver
Atul-Chahar
Use when the user wants to review Qodo PR feedback or fix code review comments.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 26, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Atul-Chahar/Foreman
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Atul-Chahar
- 0.529score
qodo-get-rules
Atul-Chahar
Loads coding rules from Qodo most relevant to the current coding task by generating a semantic search query from the assignment.
SkillBFreshness: BClaude Code +9 - 0.518score
reviewer
Atul-Chahar
Review every swarm diff before a human sees it — security checklist first, spec fidelity second.
SkillBFreshness: BClaude Code +9 - 0.518score
security-review
Atul-Chahar
A precision-first checklist applied to every diff — secrets, dynamic execution, injection, deserialization, authz.
SkillBFreshness: BClaude Code +9 - 0.518score
implementer
Atul-Chahar
Implement exactly one task spec — minimal diff, tests first, stay inside the declared scope.
SkillBFreshness: BClaude Code +9 - 0.516score
context-budget
Atul-Chahar
Token discipline for subagents — ask for listed context only, summarize instead of dumping, never request the repo tree.
SkillBFreshness: BClaude Code +9 - 0.513score
tdd-workflow
Atul-Chahar
Red, green, refactor — the failing test comes first and the spec's test command is the arbiter.
SkillBFreshness: BClaude 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 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
planner skill. Agent Mart. https://agentmart.dev/skills/atul-chahar-planner (last updated 2026-10-24)