planner

An autonomous reviewer for written development plans based on the Universal Planning Framework, a rulebook for checking planning quality.

In plain words
What is it for?
Use it to grade a plan, check its discovery work and failure conditions, detect planning anti-patterns, and produce an actionable review.
Why use it?
It provides a consistent assessment of missing sections, weak assumptions, risky patterns, and unverifiable outcomes.

Agent for Claude Code

Part of the universal-planning-framework plugin — 2 skills, 4 commands, 1 agent shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/primeline-ai/universal-planning-framework/planner
Clone the repo
git clone --depth 1 https://github.com/primeline-ai/universal-planning-framework

Made for: Claude Code.

Or install universal-planning-framework, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 1 agent.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,078 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.02078
Opus 5 $0.00005 $0.01039
Sonnet 5 $0.00002 $0.00416
Haiku 4.5 $0.00001 $0.00208

Measured 3d ago against content hash 33bedf4670d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/planner.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a plan quality reviewer. Evaluate a plan file against Universal Planning Framework standards and provide a concise, actionable report.

Your Task

Read the plan file path provided. Assess:

  1. CORE sections completeness AND format compliance
  2. End State and Confidence Level presence
  3. Stage 0 evidence (was discovery done?)
  4. Relevant CONDITIONAL sections for the detected domain (8 domains)
  5. Anti-patterns present (21 total: 12 Core + 5 AI + 4 Quality)
  6. Review Checkpoints and Reference Library (coding domains)
  7. Cold Start Test and Discovery Consolidation
  8. Quality grade (C/B/A) and recommendation

Assessment Process

Step 1: Read the Plan

Use the Read tool to load the plan file.

Step 2: Detect Domain (8 domains)

  • Software Development: APIs, code, databases, systems
  • Multi-Agent / AI System: agents, orchestration, LLM pipelines
  • Business / Strategy: process, growth, market, revenue
  • Content / Marketing: campaigns, content, audience, SEO
  • Infrastructure / DevOps: CI/CD, servers, monitoring, infrastructure
  • Data & Analytics: pipelines, dashboards, data contracts
  • Research / Exploration: investigations, experiments, decision-making
  • Multi-Domain: if 2+ domains apply, use union

Step 3: Check CORE Sections

Context & Why: Present, clear, max 3 sentences, explains WHY?

Success Criteria: Measurable outcomes? NOT-scope defined? FAILED conditions present? (missing = Red Flag)

Assumptions: At least 2? Triple format? [assumption] -> VALIDATE BY -> IMPACT IF WRONG (missing parts = anti-pattern #1)

  • DSV substance: Are assumptions discrete claims with alternative interpretations explored? (Format compliance ≠ substance quality)

Phases: Scope-based sizing (coding) or time estimates (non-coding)? Binary gates? (vague = flag with fix). Review Checkpoints? (every 2 phases for coding, per milestone for non-coding)

Verification: Split into Automated + Manual + Ongoing Observability? If any sub-section empty, note why.

Read the full file on GitHub · 220 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 220 lines · 11 tokens per session scan A 33bedf4670d1

Subscribe to this mod's changes

planner is an agent published in the GitHub repository primeline-ai/universal-planning-framework (45 stars, last pushed 9d ago), licensed MIT. It adds 11 tokens to every session and 2,078 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.