mcp-todo

A skill for managing TODO items in an MCP Server workflow. MCP is a standard way for an agent to use connected tools, and this skill routes TODO operations through that workflow instead of editing storage files directly.

In plain words
What is it for?
It helps list, search, read, create, update, complete, and delete MCP Server TODO items.
Why use it?
It prevents TODO data from being changed through the wrong file or format and keeps operations consistent with the workflow.

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/sharpninja/mcpserver/mcp-todo
Any agent
npx skills add sharpninja/McpServer --skill mcp-todo
Clone the repo
git clone --depth 1 https://github.com/sharpninja/McpServer

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,865 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 $0.00062 $0.01865
Opus 5 $0.00031 $0.00932
Sonnet 5 $0.00012 $0.00373
Haiku 4.5 $0.00006 $0.00186

Measured 2d ago against content hash c3a970d84515, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-todo 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.

skills/mcp-todo/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server TODO Management

This skill teaches an agent to query and mutate MCP Server TODO items through the plugin (workflow.todo.*) instead of touching storage files. In this workspace, "TODO" always means an MCP Server TODO item: not Claude Code's in-session task list, not a markdown checklist, and not a GitHub issue list.

When to Use

  • The user says: "list todos", "open TODOs", "create a todo", "update todo", "mark todo done", "check todo status", "plan implementation", "query tasks".
  • You need the current TODO backlog, a single TODO by id, or to record progress on an item you are implementing.
  • You discover work that must be tracked as a persisted TODO.

When Not to Use

  • Tracking ephemeral, in-session steps for yourself: use the harness task list, not MCP TODOs.
  • Session logging, requirements (FR/TR), or GraphRAG operations: those are separate plugin surfaces (workflow.sessionlog.*, requirements docs, GraphRAG), not workflow.todo.*.
  • Any time the only goal is to read docs/Project/TODO.yaml "quickly". That is still forbidden; use workflow.todo.query / workflow.todo.get.

Inputs

  • A TODO id for get/select/update/delete (canonical format, see Critical Rules).
  • For query: optional filters keyword, priority (critical|high|medium|low), section, and done (boolean).
  • For create: required id, title, section, priority; optional estimate, description (string array), technicalDetails, implementationTasks ({task, done}), note, remaining, dependsOn, functionalRequirements, technicalRequirements.
  • For update: id plus only the fields you want to change (same shape as create, plus done, completedDate, doneSummary).

Critical Rules

  1. NEVER read or write TODO.yaml, docs/Project/TODO.yaml, or any TODO storage file directly with Read, Edit, Write, Grep, or shell cat. The plugin is the only allowed interface. A "quick lookup" is still a violation.
  2. Route every operation through the Claude Code plugin (mcpserver-claude-code-plugin) using workflow.todo.* methods. "Not in the visible tool list" does not mean unavailable; use the documented wrapper form.
  3. Persisted TODO ids must match ^[A-Z][A-Z0-9]*(?:-[A-Z0-9]+)+-\d{3}$ (uppercase kebab-case, three-digit suffix) or ^ISSUE-\d+$. Valid: PLAN-NAMINGCONVENTIONS-001, MCP-TODO-CREATE-001, ISSUE-17. Invalid: plan-api-001, MCP-API-42, MCP-001, ISSUE-ABC.
  4. To create a GitHub-backed TODO, submit the special id ISSUE-NEW. The server creates the issue, rewrites the saved id to the canonical ISSUE-{number}, and returns that id. After first sync, ISSUE-{number} descriptions are immutable; updates surface to GitHub as a comment, not a body rewrite.
  5. Each dependsOn entry must itself be a valid persisted TODO id.
  6. Do not invent methods or fields. The only TODO methods are listed in Workflow.
  7. Every request needs a unique requestId, format req-<yyyyMMddTHHmmssZ>-<seq-or-slug>, unique within the session.

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 62 tokens per session scan A c3a970d84515

Subscribe to this mod's changes

mcp-todo is a skill published in the GitHub repository sharpninja/McpServer (2 stars, last pushed 11d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,865 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 2026-08-31.