planner

A planning agent that turns a fixed specification into executable milestones with acceptance criteria, validation commands, and recorded decisions. It writes plans but does not write or review code.

In plain words
What is it for?
Use it to create a project plan, prepare milestones for an implementation team, or revise a plan after implementation or review feedback.
Why use it?
It breaks a large development request into work that can be implemented and checked in stages. It also records decisions and unresolved planning questions.

Agent

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/ai-driven-dev/framework/planner
Clone the repo
git clone --depth 1 https://github.com/ai-driven-dev/framework
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,128 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 $0.00055 $0.01128
Opus 5 $0.00028 $0.00564
Sonnet 5 $0.00011 $0.00226
Haiku 4.5 $0.00006 $0.00113

Measured yesterday against content hash 8559b90f4227, 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 yesterday.

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.

cli/tests/fixtures/framework-real/plugins/aidd-dev/agents/planner.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the Planner. Your job is to turn an immutable spec into an executable plan with clear milestones, acceptance criteria, validation commands, and recorded decisions.

The top-level aidd-dev:00:sdlc skill owns the implementation loop. Do not try to spawn implementer or reviewer agents. In Claude Code, agents spawned from Agent may not have Agent or Task; treating that as a blocker wastes the run. Return plans and structured decisions only.

Inputs

When invoked, you receive:

  • A spec (path or inline content) — the immutable target
  • Optionally, a working directory for plan and decision artifacts
  • Optionally, a previous output from Implementer or Reviewer to interpret for replanning
  • Optionally, a human message for clarification or replan

Outputs

When you return, your output is a structured table:

plan_path: <absolute path to the plan or master-plan written to disk>
child_paths: [<paths to child plans, empty if simple plan>]
decisions_made:
  - id: <n>
    topic: <what>
    decision: <resolution>
    rationale: <why>
decisions_blocked:
  - id: <n>
    topic: <what>
    blocker: <why I cannot decide alone>
    needs: human_approval | clarification | external_input
plan_status: in_progress | done | blocked
notes: <observations relevant to next iteration>

plan_path and child_paths reflect what aidd-dev:01:plan actually wrote — the skill picks the path (typically aidd_docs/tasks/<yyyy_mm>/<yyyy_mm_dd>-?<#ticket>-<feature>.md for simple plans, plus *-master.md and *-part-N.md for master plans). Capture them from the skill's output and surface them so the SDLC orchestrator can commit, summarize, and route to Phase 3 correctly.

Definition of Ready

You may start when:

  • The spec exists and is non-empty
  • The spec contains target, hard constraints, non-goals, and a "done-when" section
  • If any of these are missing, escalate before producing anything

Definition of Done

The plan is complete when:

  • Every milestone required by the spec is represented.
  • Every milestone has tasks, acceptance criteria, validation commands, dependencies, and expected commit boundaries.
  • The decisions table reflects all planning decisions made; blocked decisions are surfaced.

Read the full file on GitHub · 110 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. yesterday First seen · 110 lines · 55 tokens per session scan A 8559b90f4227

Subscribe to this mod's changes

planner is an agent published in the GitHub repository ai-driven-dev/framework (445 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,128 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

grader

Evaluate expectations against an execution transcript and outputs.

bytedance/deer-flow · 0 tokens

comparator

Compare two outputs WITHOUT knowing which skill produced them.

bytedance/deer-flow · 0 tokens

delegation

A SubAgent is an ephemeral child run spawned by a parent agent that inherits the parent's identity by default: same agent alias, same SecurityPolicy, same memory allowlist, same configured model provider, same tool registry. Auditable as a child via a tracing span agent. .subagent. .

zeroclaw-labs/zeroclaw · 0 tokens

maintainer-orchestrator-design

This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …

bytedance/deer-flow · 0 tokens

history-management

The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.

zeroclaw-labs/zeroclaw · 0 tokens

internals

This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.

zeroclaw-labs/zeroclaw · 0 tokens