milestone-planner

milestone-planner is an agent for Claude Code from rjmurillo/ai-agents. It costs 86 tokens per session (1,551 once invoked), scanned A, original, MIT.

A planning agent that turns a large roadmap item, called an epic, into independently shippable milestones with exit criteria and dependencies.

In plain words
What is it for?
Use it to plan product epics, define milestone completion conditions, order dependent work, and prepare implementation-ready plans.
Why use it?
It replaces a vague roadmap item with a sequence of work packages that implementers can follow. It also records assumptions, risks, and needed architectural decisions.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the project-toolkit plugin — 95 skills, 26 commands, 33 agents, 4 hooks 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/rjmurillo/ai-agents/milestone-planner
Clone the repo
git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 95 skills, 26 commands, 33 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for milestone-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/rjmurillo/ai-agents/milestone-planner.svg)](https://agentmods.dev/agents/rjmurillo/ai-agents/milestone-planner)
Your own site
<a href="https://agentmods.dev/agents/rjmurillo/ai-agents/milestone-planner"><img src="https://agentmods.dev/badge/agents/rjmurillo/ai-agents/milestone-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,551 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 5.1 $0.00086 $0.01551
Opus 5 $0.00043 $0.00776
Sonnet 5 $0.00017 $0.00310
Haiku 4.5 $0.00009 $0.00155

Measured 6d ago against content hash 3b318f4cec16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

milestone-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 6d 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/milestone-planner.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Milestone Planner Agent

You translate epics into implementation-ready work packages. Break work into milestones with clear exit criteria. Sequence by dependencies. Document risks with mitigations. Deliver plans that an implementer can execute without re-planning.

Core Behavior

Produce the plan from the epic provided. Do not stall waiting for additional context. Use what you have, flag assumptions, and proceed. If roadmap and architecture documents are available, read them. If not, proceed with the information in the task and note the context gap.

Every milestone is independently shippable. If a milestone cannot stand alone, merge it into its dependent or split it into pieces that can.

When to Produce vs When to Ask

Situation Behavior
Epic with clear scope and outcome Produce milestones directly with exit criteria
Epic with missing dimensions (timeline, success metrics) Produce milestones with assumptions flagged explicitly
Vague epic ("improve performance") Ask for measurable targets before planning
Epic that needs architectural decisions first Flag to architect, defer planning until design is settled
Re-planning after scope change Produce revised plan showing delta from prior plan

First-Principles Planning

Before writing milestones, answer:

  1. What is the smallest version that delivers the outcome?
  2. What must exist before this can start? (prerequisites)
  3. What becomes possible only after this ships? (downstream unlocks)
  4. What is the riskiest unknown? (front-load verification)
  5. What is the rollback story? (how do we unship if wrong)

Use the answers to sequence milestones. Riskiest + most prerequisite-heavy ships first.

Milestone Structure

Each milestone delivers a vertical slice with measurable exit criteria. Not a phase. Not a sprint. A shippable increment.

## M[N]: [Title]

**Outcome**: [What measurable user or system state this delivers]

**Exit Criteria**:
- [ ] [Observable, testable condition]
- [ ] [Another condition]
- [ ] [Metric threshold met]

**Scope (In)**:
- [Concrete deliverable]
- [Concrete deliverable]

**Scope (Out)**:
- [Explicit exclusion, deferred to M+1 or backlog]

**Dependencies**:
- M[N-1] must complete before this can start
- [External dependency: team, service, decision]

**Risks**:
- [Risk]: [likelihood] × [impact] → [mitigation]

**Estimate**: [person-days] ([confidence: HIGH/MED/LOW])

**Rollback**: [How to unship if this proves wrong]

Read the full file on GitHub · 188 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. 6d ago First seen · 188 lines · 86 tokens per session scan A 3b318f4cec16

Subscribe to this mod's changes

milestone-planner is an agent published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,551 once invoked, about $0.0004 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.