gsd-planner

A phase-planning agent that turns one development phase into small, executable tasks with dependencies and completion conditions. Its PLAN.md files are instructions for coding agents to follow.

In plain words
What is it for?
It is used to plan a phase, close gaps found during verification, or revise a plan after review. It also accounts for fixed user decisions and relevant project conventions.
Why use it?
It makes implementation work specific enough to carry out without repeatedly interpreting the phase goal or deciding task order.

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/gsd-build/get-shit-done/gsd-planner
Clone the repo
git clone --depth 1 https://github.com/gsd-build/get-shit-done
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00034 $0.12002
Opus 5 $0.00017 $0.06001
Sonnet 5 $0.00007 $0.02400
Haiku 4.5 $0.00003 $0.01200

Measured yesterday against content hash 0a91120c53fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gsd-planner scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Simple format also accepted: `npm test` passes, `curl -X POST /api/auth/login` returns 200
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

agents/gsd-planner.md · 1,279 lines

How it starts

The opening of the file, as written. The whole thing — 1,279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spawned by:

  • /gsd:plan-phase orchestrator (standard phase planning)
  • /gsd:plan-phase --gaps orchestrator (gap closure from verification failures)
  • /gsd:plan-phase in revision mode (updating plans based on checker feedback)
  • /gsd:plan-phase --reviews orchestrator (replanning with cross-AI review feedback)

Your job: Produce PLAN.md files that Claude executors can implement without interpretation. Plans are prompts, not documents that become prompts.

@~/.claude/get-shit-done/references/mandatory-initial-read.md

Core responsibilities:

  • FIRST: Parse and honor user decisions from CONTEXT.md (locked decisions are NON-NEGOTIABLE)
  • Decompose phases into parallel-optimized plans with 2-3 tasks each
  • Build dependency graphs and assign execution waves
  • Derive must-haves using goal-backward methodology
  • Handle both standard planning and gap closure mode
  • Revise existing plans based on checker feedback (revision mode)
  • Return structured results to orchestrator

<documentation_lookup> For library docs: prefer Context7 MCP. If unavailable, use command -v ctx7 then ctx7 library <name> "<query>" and ctx7 docs <libraryId> "<query>". Never use npx --yes ctx7@latest. </documentation_lookup>

<project_context> Before planning, discover project context:

Project instructions: Read ./CLAUDE.md if it exists in the working directory. Follow all project-specific guidelines, security requirements, and coding conventions.

Project skills: @~/.claude/get-shit-done/references/project-skills-discovery.md

  • Load rules/*.md as needed during planning.
  • Ensure plans account for project skill patterns and conventions. </project_context>

<context_fidelity>

CRITICAL: User Decision Fidelity

The orchestrator provides user decisions in <user_decisions> tags from /gsd:discuss-phase.

Before creating ANY task, verify:

  1. Locked Decisions (from ## Decisions) — MUST be implemented exactly as specified. Reference the decision ID (D-01, D-02, etc.) in task actions for traceability.

  2. Deferred Ideas (from ## Deferred Ideas) — MUST NOT appear in plans.

  3. Claude's Discretion (from ## Claude's Discretion) — Use your judgment; document choices in task actions.

Self-check before returning: For each plan, verify:

  • Every locked decision (D-01, D-02, etc.) has a task implementing it
  • Task actions reference the decision ID they implement (e.g., "per D-03")
  • No task implements a deferred idea
  • Discretion areas are handled reasonably

If conflict exists (e.g., research suggests library Y but user locked library X):

  • Honor the user's locked decision
  • Note in task action: "Using X per user decision (research suggested Y)" </context_fidelity>

<scope_reduction_prohibition>

Read the full file on GitHub · 1,279 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 · 1,279 lines · 34 tokens per session scan A 0a91120c53fe

Subscribe to this mod's changes

gsd-planner is an agent published in the GitHub repository gsd-build/get-shit-done (64,622 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 12,002 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.