productplan-pm

productplan-pm is a skill for Claude Code, Codex from olgasafonova/productplan-mcp-server. It costs 51 tokens per session (2,060 once invoked), scanned A, original, MIT.

A set of instructions for product managers using ProductPlan, a tool for planning product work. It covers roadmaps, objectives and key results, ideas, feature timelines, launches, and customer feedback.

In plain words
What is it for?
Viewing roadmaps, adding or rescheduling features, moving features between categories, tracking objectives, and reviewing ideas or feedback.
Why use it?
It explains how to find the right ProductPlan records and use their IDs, reducing mistakes when viewing or changing product information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Viewing roadmaps, adding or rescheduling features, moving features between categories, tracking objectives, and reviewing ideas or feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/olgasafonova/productplan-mcp-server/productplan-pm
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.

Any agent
npx skills add olgasafonova/productplan-mcp-server --skill productplan-pm
Clone the repo
git clone --depth 1 https://github.com/olgasafonova/productplan-mcp-server

Made for: Claude Code, Codex.

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 productplan-pm

README.md
[![agentmods](https://agentmods.dev/badge/skills/olgasafonova/productplan-mcp-server/productplan-pm/github.svg)](https://agentmods.dev/skills/olgasafonova/productplan-mcp-server/productplan-pm)
Your own site
<a href="https://agentmods.dev/skills/olgasafonova/productplan-mcp-server/productplan-pm"><img src="https://agentmods.dev/badge/skills/olgasafonova/productplan-mcp-server/productplan-pm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for productplan-pm

Your own site · 80×15
<a href="https://agentmods.dev/skills/olgasafonova/productplan-mcp-server/productplan-pm"><img src="https://agentmods.dev/badge/skills/olgasafonova/productplan-mcp-server/productplan-pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,060 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00051 $0.02060
Opus 5.5 $0.00020 $0.00824
Sonnet 5.5 $0.00010 $0.00412
Haiku 4.5 $0.00005 $0.00206

Measured 1mo ago against content hash 456536556e46, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

productplan-pm 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 1mo 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.

skills/productplan-pm/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProductPlan for Product Managers

Complete toolkit for day-to-day product management in ProductPlan.

The ID Chain Pattern

ProductPlan tools require IDs. Always list first, then drill down:

list_roadmaps → roadmap_id → get_roadmap_bars → bar_id → get_bar
list_objectives → objective_id → get_objective → key_result data
list_ideas → idea_id → get_idea → customer/tag data

Roadmap Management

View your roadmap

  1. Call list_roadmaps to get roadmap IDs
  2. Call get_roadmap_complete with roadmap_id for all data in one call
    • Returns bars, lanes, and milestones together
    • Faster than separate calls

Add a new feature

  1. Get roadmap_id from list_roadmaps
  2. Get lane_id from get_roadmap_lanes (pick the category)
  3. Call manage_bar with:
    • action="create"
    • roadmap_id, lane_id
    • name, start_date, end_date (YYYY-MM-DD)

Reschedule a feature

  1. Get bar_id from get_roadmap_bars
  2. Call manage_bar with action="update", bar_id, new start_date and end_date

Move feature to different lane

  1. Get bar_id from get_roadmap_bars
  2. Get target lane_id from get_roadmap_lanes
  3. Call manage_bar with action="update", bar_id, lane_id

Create feature dependencies

  1. Get both bar IDs from get_roadmap_bars
  2. Call manage_bar_connection with action="create", bar_id (source), target_bar_id

Read comments on features

Call get_bar_comments with bar_id. The ProductPlan API has no endpoint for writing comments.

Link external resources

Call manage_bar_link with action="create", bar_id, url, name. The link is a plain web link: an Azure DevOps or Jira integration link can only be made in the ProductPlan UI.

Color bars

Bar color comes from the roadmap's legend, set by name.

  1. Call get_roadmap_legends with roadmap_id to get the legend names
  2. Call manage_bar with action="update", bar_id, legend="" (matched case-insensitively)
  3. To remove a color, pass clear_legend=true

Never pass legend_id: ProductPlan reads it as "clear the color", so the server refuses it.

Read the full file on GitHub · 244 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. 1mo ago Changed · +18 lines 456536556e46
  2. 1mo ago First seen · 226 lines · 51 tokens per session scan A 2f93334bd01b

Subscribe to this mod's changes

productplan-pm is a skill published in the GitHub repository olgasafonova/productplan-mcp-server (3 stars, last pushed 13d ago), licensed MIT. It adds 51 tokens to every session and 2,060 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.