planner-agent
Receives a seed intent (and optional loop context on re-plan) and produces a validated ExecutionPlan using only TYPE 2 tools.
Skill by tooensure
Chalk Labs
Need help deploying planner-agent?
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/shawn2024bellazan-prog-planner-agent
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: agent-building
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-agent
Tools it pre-approves 9
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
load_skillread_skill_resourcetrail.gettrail.queryReadFileListDirectorySearchFilesGrepContentGetFileInfo
What's inside
- Skill name
planner-agent- Description
- Receives a seed intent (and optional loop context on re-plan) and produces a validated ExecutionPlan using only TYPE 2 tools. Load when the Orchestrator routes to the PLAN phase. Do not load if no seed intent is present.
- License
- Proprietary — Tooensure LLC
- Compatibility
- Requires pmcro-framework. MAF 1.6.1+, MCP 1.3.0+. Reads the filesystem and skill resources via TYPE 2 tools only.
- Allowed tools
- load_skill, read_skill_resource, trail.get, trail.query, ReadFile, ListDirectory, SearchFiles, GrepContent, GetFileInfo
- Metadata
- tier: PHASE · author: tooensure · pattern: Pattern 2 — Deliberative · version: 1.0.0 · proven-in: PMCRO framework design session 2026-05-19 · thoughtlock: 2026-05-19
- Instructions
- 117 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- evals.json · evals/
- type2-tool-allowlist.md · references/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from shawn2024bellazan-prog/PMCRO-Cognitive-Archecture
- 0.474score
compliance-check
projectname-platform
Verify that an action or output satisfies a named compliance framework (SOC2, GDPR, HIPAA, ISO27001).
SkillCFreshness: CClaude Code +9 - 0.471score
maker-agent
tooensure
Executes deterministic plan steps strictly as written without deliberation.
SkillCFreshness: CClaude Code +9 - 0.471score
governance
projectname-platform
Apply the active governance policy to any agent action or output.
SkillCFreshness: CClaude Code +9 - 0.471score
orchestrator-agent
tooensure
Routes the PMCRO loop, guards MaxLoops, persists TrailFrames, and is the ONLY agent that dispatches TYPE 1 tools after HIL approval.
SkillCFreshness: CClaude Code +9 - 0.469score
reflector
tooensure
Chain-of-thought reasoning and self-critique agent.
SkillCFreshness: CClaude Code +9 - 0.468score
pmcro-framework
tooensure
ROOT identity for the PMCRO agent system.
SkillCFreshness: CClaude Code +9 - 0.467score
orchestrator
tooensure
Routing and handoff protocols for the Orchestrator agent.
SkillCFreshness: CClaude Code +9 - 0.467score
validator
tooensure
Utility-based scorer.
SkillCFreshness: CClaude Code +9 - 0.467score
reactive
tooensure
Fast reflex responder.
SkillCFreshness: CClaude Code +9 - 0.467score
reflector-agent
tooensure
Receives checker_frame_json and the full loop trail, writes EarnedConstraints if patterns warrant them, and issues the loop verdict: ACCEPT, LOOP, or ESCALATE.
SkillCFreshness: CClaude Code +9 - 0.467score
markdown-format
projectname-platform
Format any response as clean, readable Markdown with appropriate headers, code blocks, and tables.
SkillCFreshness: CClaude Code +9 - 0.467score
checker-agent
tooensure
Scores Maker output on three dimensions: completeness, correctness, and law compliance.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 21, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- Proprietary — Tooensure LLC
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tooensure
- 0.474score
auditor
tooensure
Governance auditor for the PMCRO agent system.
SkillCFreshness: CClaude Code +9 - 0.471score
orchestrator-agent
tooensure
Routes the PMCRO loop, guards MaxLoops, persists TrailFrames, and is the ONLY agent that dispatches TYPE 1 tools after HIL approval.
SkillCFreshness: CClaude Code +9 - 0.471score
maker-agent
tooensure
Executes deterministic plan steps strictly as written without deliberation.
SkillCFreshness: CClaude Code +9 - 0.469score
beacon-address-scraper
tooensure
Scrapes Ramsey County Beacon property detail pages for all addresses in vb-pins.csv using the live Playwright MCP server (localhost:7032/mcp).
SkillCFreshness: CClaude Code +9 - 0.469score
reflector
tooensure
Chain-of-thought reasoning and self-critique agent.
SkillCFreshness: CClaude Code +9 - 0.468score
pmcro-framework
tooensure
ROOT identity for the PMCRO agent system.
SkillCFreshness: CClaude 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-agent 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-agent skill. Agent Mart. https://agentmart.dev/skills/shawn2024bellazan-prog-planner-agent (last updated 2026-10-24)