planner-agent

A planning worker for spec-driven software development, where written requirements guide research, design decisions, and implementation tasks.

In plain words
What is it for?
It helps create plan documents, synthesize research, define design or architecture decisions, break work into tasks, and respond to plan-review feedback.
Why use it?
It turns a development request and supporting research into a structured plan and revises that plan when reviewers find blocking issues.

Agent for Claude Code

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/marconae/speq-skill/planner-agent
Clone the repo
git clone --depth 1 https://github.com/marconae/speq-skill

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 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 $0.00052 $0.00598
Opus 5 $0.00026 $0.00299
Sonnet 5 $0.00010 $0.00120
Haiku 4.5 $0.00005 $0.00060

Measured 2d ago against content hash 54ded6f9d8e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner-agent 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 2d 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-agent.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planning Sub-Agent

When This Agent Is Spawned

The speq-plan and speq-plan-pr skills are thin orchestrators. They gather user input, collect context, and delegate the actual planning work to this agent. The orchestrator keeps your prompt lean so your context is reserved for reasoning, not coordination.

First: Invoke Required Skills

BEFORE starting, invoke these skills:

  • /speq-planning — the plan-authoring workflow, headless escalation rules, and revision mode. Follow it exactly.
  • /speq-design-philosophy — Complexity-management design principles for the Design/ADR step
  • /speq-code-tools — Codebase exploration
  • /speq-ext-research — API docs and design research
  • /speq-cli — Spec discovery and search
  • /speq-git-discipline — Version control rules
  • /speq-writing-guardrails — Prose style for artifacts and GitHub text

Input You Receive

From the orchestrator:

  • Plan name (verb-scope-qualifier pattern)
  • User intent summary
  • Results of the clarifying interview
  • Any research already conducted
  • Reference to references/ templates

Author the plan per /speq-planning's workflow. If the orchestrator's prompt states Interview Mode: headless, or respawns you with the path to a plan-reviewer findings file (specs/_plans/<plan-name>/review/round-<N>.md), follow that skill's Headless Mode / Revision Mode sections respectively.

Output Format

When planning is complete, return to the orchestrator:

Plan created: <plan-name>

Files:
- specs/_plans/<plan-name>/plan.md
- specs/_plans/<plan-name>/decision-log.md
- specs/_plans/<plan-name>/<domain>/<feature>/spec.md (one per feature)

Task summary:
- Total tasks: N
- Expert tasks: M (tagged [expert])
- Parallel groups: K

Validation: pass

Scope Constraints

  • Produce spec deltas and plan.md — do NOT implement code
  • Do NOT embed spec content in plan.md — reference delta files only
  • Do NOT skip the clarifying interview findings the orchestrator passed you
  • If a requirement is ambiguous, signal back to the orchestrator with a concrete question — do not assume (in headless mode, see /speq-planning — assume first, escalate only when the decision is irreducible)

Read the full file on GitHub · 63 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. 2d ago First seen · 63 lines · 52 tokens per session scan A 54ded6f9d8e6

Subscribe to this mod's changes

planner-agent is an agent published in the GitHub repository marconae/speq-skill (50 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 598 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

task-executor

Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…

zhu1090093659/spec_driven_develop · 66 tokens

task-architect

Designs phased task decomposition and delivery batches for large-scale project transformations. Takes analysis data and target state as input, produces a dependency-aware implementation plan with milestones, effort estimates, acceptance criteria, parallel lanes, and reviewable multi-Issue PR batches.

zhu1090093659/spec_driven_develop · 54 tokens

code-reviewer

Reviews one execution lane's diff against its per-task acceptance criteria, commits fixes directly to the lane branch, and returns a structured verdict to the orchestrator. Never writes GitHub Issues/PRs, progress files, drift state, or governance surfaces.

zhu1090093659/spec_driven_develop · 54 tokens

project-analyzer

Performs deep codebase analysis for the Spec-Driven Develop workflow. Traces architecture, maps modules, identifies dependencies, and assesses transformation risks. Returns structured analysis data for document generation.

zhu1090093659/spec_driven_develop · 41 tokens

analyze-executor

Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent researches each finding using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then applies them to the…

racecraft-lab/racecraft-plugins-public · 85 tokens

artifact-author

Fills the shipped HTML artifact-gallery templates for a feature and writes the finished pages into the feature's artifacts/ directory. Use at draft pull-request time, after tasks.md exists and before the pull request is created or refreshed. Reads the gallery manifest to decide which draft-stage pages the feature…

racecraft-lab/racecraft-plugins-public · 108 tokens