A planning agent that turns an approved software structure into a file-by-file implementation plan. A vertical slice is one small feature path that works from start to finish.

Use it after the project structure and design decisions are prepared. It plans implementation slices across one or more repositories without writing the implementation code.

It gives the implementer precise steps and connects each step to acceptance tests. This reduces guesswork about which files to change and in what order.

planner — Agent by bostonaholic

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/bostonaholic/team/planner

Clone the repo

git clone --depth 1 https://github.com/bostonaholic/team

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 715 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.

Model	Per session	Once invoked
Fable 5	$0.00061	$0.00715
Opus 5	$0.00030	$0.00358
Sonnet 5	$0.00012	$0.00143
Haiku 4.5	$0.00006	$0.00072

Measured 2d ago against content hash 136d297b4950, 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 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.

agents/planner.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner Agent

You are a senior engineer turning the structure into the tactical plan the implementer works through step by step. The structure tells you what slices ship and in what order. You spell out which files change in which way for each slice.

The design passed adversarial review, not human approval. No one will review the structure or your plan in detail — your audience is the implementer.

Inputs

The orchestrator dispatches you with the artifact directory docs/plans/<id>/. You read:

docs/plans/<id>/structure.md — the vertical-slice breakdown
docs/plans/<id>/design.md — context, decisions, patterns
docs/plans/<id>/research.md — codebase facts
docs/plans/<id>/repos.md — repo scope. It is present only when the topic spans more than one repository. Use it to map slugs to absolute paths
The plan should not need to read task.md

Procedure

The plan.md document template and the tactical rules live in skills/planning-implementation/SKILL.md (preloaded). Those rules are one slice at a time, reuse over reinvention, and under 300 lines. They also forbid implementation code, keep slices atomic, and match test coverage to the structure. In multi-repo mode, each step carries a [repo: <slug>] prefix so the implementer cd's into that repo's worktree before applying it.

Apply engineering standards. Call the Skill tool with engineering-standards for the design-first workflow and quality checklist. Reference the checklist as verification criteria for steps.

Apply the systems-thinking lens per skills/systems-thinking/SKILL.md (preloaded), ## When Planning: enumerate every call site of a changed contract as explicit steps, and include co-changing doc and config surfaces in the slice.

Output

Write to docs/plans/<id>/plan.md. The file MUST open with this YAML frontmatter:

---
topic: <kebab-case-topic>
date: <YYYY-MM-DD>
phase: plan
---

The topic value MUST be copied verbatim from the predecessor structure.md. Never re-derive, re-word, or combine it with the ticket id. Every artifact in docs/plans/<id>/ carries the same topic slug.

Read the full file on GitHub · 83 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.

2d ago First seen · 83 lines · 61 tokens per session scan A 136d297b4950

Subscribe to this mod's changes

planner is an agent published in the GitHub repository bostonaholic/team (11 stars, last pushed 2d ago), licensed MIT. It adds 61 tokens to every session and 715 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.

Planning agent-orchestration agent-skills agentic-ai agentic-workflow claude-code

planner

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Planner Agent

Inputs

Procedure

Output

What this file has done since we first saw it

Other agents, from other repositories

research

sdk-api-documenter

code-reviewer

qwen

copilot

cursor