sb-plan

sb-plan is a skill for Claude Code, Codex from stablebaseline/mcp. It costs 113 tokens per session (2,032 once invoked), scanned A, original, MIT.

A workflow for creating and managing plans, phases, tasks, dependencies, people responsible, and dates in Stable Baseline, a planning and task-tracking system.

In plain words
What is it for?
Creating plans, adding phases or tasks, assigning work, changing dates, marking tasks complete, setting dependencies, and updating timelines.
Why use it?
It keeps work organized in the correct project hierarchy and checks existing records before making changes, reducing duplicate tasks and incorrect updates.

Skill for Claude CodeCodex

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 skills/stablebaseline/mcp/sb-plan
Any agent
npx skills add stablebaseline/mcp --skill sb-plan
Clone the repo
git clone --depth 1 https://github.com/stablebaseline/mcp

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 sb-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/stablebaseline/mcp/sb-plan.svg)](https://agentmods.dev/skills/stablebaseline/mcp/sb-plan)
Your own site
<a href="https://agentmods.dev/skills/stablebaseline/mcp/sb-plan"><img src="https://agentmods.dev/badge/skills/stablebaseline/mcp/sb-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,032 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 $0.00113 $0.02032
Opus 5 $0.00056 $0.01016
Sonnet 5 $0.00023 $0.00406
Haiku 4.5 $0.00011 $0.00203

Measured 3d ago against content hash b07795f75c54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sb-plan 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 3d 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.

microsoft/cowork-plugin/skills/sb-plan/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stable Baseline: plans and tasks

What this skill does

Builds and maintains structured plans: phases, tasks, dependencies, assignees and dates. Every change runs under the signed in user's own Stable Baseline identity.

IDs are never hardcoded. Resolve projectId, planId, phaseId and task IDs at runtime from listing calls made in this conversation.

The hierarchy

Project contains plans, a plan contains phases, a phase contains tasks. Work down it, never guess a level.

  • listPlans requires projectId
  • listPlanPhases and getPlanHierarchy for the structure
  • listTasks requires planId

Before you change anything

  1. Resolve scope. listOrganisations, listWorkspaces, listProjects. Ask if several projects are accessible.
  2. Check what exists. listPlans with a query before creating a plan. listTasks before adding a task that may already be there. Duplicate tasks are the most common failure when working from a transcript.
  3. Read the current state before editing. getPlan, getPlanPhase or getTask so you know what you are changing.

Creating

  • createPlan requires projectId and title. It also takes description, status, priority, start_date, end_date and linked_documents. Link the source document when there is one; it is what makes the plan traceable.
  • createPlanPhase for a phase.
  • createTask requires planId and title. It also takes phaseId, description, type, status, priority, acceptance_criteria and checklist.

acceptance_criteria and checklist both replace the whole array on update, and array order is display order. To change one row, fetch the item with getTask, modify the array, and send the whole thing back. Echo back each existing row id you keep, so the server's per-row attribution, who added or completed it and when, survives the round trip.

Write real acceptance criteria when the user has given you enough to work with. A task titled "fix auth" with no criteria helps nobody.

Read the full file on GitHub · 186 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. 3d ago First seen · 186 lines · 113 tokens per session scan A b07795f75c54

Subscribe to this mod's changes

sb-plan is a skill published in the GitHub repository stablebaseline/mcp (0 stars, last pushed 8d ago), licensed MIT. It adds 113 tokens to every session and 2,032 once invoked, about $0.0006 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 2026-08-31.

Related

Other skills, from other repositories

wayfinder

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

mattpocock/skills · 46 tokens

sap-transport-overview

System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…

arc-mcp/arc-1 · 106 tokens

timeline-creator

Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.

mhattingpete/claude-skills-marketplace · 47 tokens

okx-task-watch

监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…

nirholas/three.ws · 138 tokens

pm-all

Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).

wei63w/pm-manager · 8 tokens

bootstrap-prd

Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.

joshukraine/dotfiles · 25 tokens