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.
npx skills add Saenai/microsoft-todo-safe-mcp --skill microsoft-todo-safe-mcpgit clone --depth 1 https://github.com/Saenai/microsoft-todo-safe-mcpWrote 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.
[](https://agentmods.dev/skills/saenai/microsoft-todo-safe-mcp/microsoft-todo-safe-mcp)<a href="https://agentmods.dev/skills/saenai/microsoft-todo-safe-mcp/microsoft-todo-safe-mcp"><img src="https://agentmods.dev/badge/skills/saenai/microsoft-todo-safe-mcp/microsoft-todo-safe-mcp/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.
<a href="https://agentmods.dev/skills/saenai/microsoft-todo-safe-mcp/microsoft-todo-safe-mcp"><img src="https://agentmods.dev/badge/skills/saenai/microsoft-todo-safe-mcp/microsoft-todo-safe-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00067 | $0.01595 |
| Opus 5 | $0.00034 | $0.00797 |
| Sonnet 5 | $0.00013 | $0.00319 |
| Haiku 4.5 | $0.00007 | $0.00160 |
Grade A, and why
microsoft-todo-safe-mcp 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 11d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 301 B
- references/operations.md 1.8 KB
- scripts/install.ps1 4.1 KB runs code
- scripts/mcp_smoke.mjs 3.1 KB runs code
- scripts/validate_agentskill.mjs 2.6 KB runs code
- server/.cursorignore 83 B
- server/.prettierignore 347 B
- server/.prettierrc 131 B
- server/CLAUDE.md 1.4 KB
- server/docs/AZURE_APP_REGISTRATION.md 6.0 KB
- server/docs/DECISIONS.md 9.0 KB
- server/docs/FOLDER_ORGANIZATION_GUIDE.md 4.4 KB
- server/docs/REPOSITORY_EVALUATION.md 20 KB
- server/docs/SAFE_PLAN_WORKFLOW.md 3.4 KB
- server/docs/STANDARD_BUILD_COMMANDS.md 4.5 KB
- server/docs/superpowers/plans/2026-06-10-propose-plan.md 2.9 KB
- server/docs/superpowers/specs/2026-06-10-propose-plan-design.md 1.9 KB
- server/LICENSE 1.2 KB
- server/package.json 3.7 KB
- server/pnpm-lock.yaml 63 KB
- server/README.md 7.6 KB
- server/scripts/analyze-low-maintenance.ts 2.0 KB runs code
- server/scripts/auth-device.test.ts 3.4 KB runs code
- server/scripts/auth-device.ts 11 KB runs code
- server/scripts/backup-export.test.ts 5.2 KB runs code
- server/scripts/doctor.test.ts 2.6 KB runs code
- server/scripts/doctor.ts 14 KB runs code
- server/scripts/export-backup.ts 2.4 KB runs code
- server/scripts/export-completed-archive.ts 2.3 KB runs code
- server/scripts/low-maintenance-analysis.test.ts 3.3 KB runs code
- server/scripts/oauth-refresh.test.ts 1.2 KB runs code
- server/scripts/plan-proposer.test.ts 7.5 KB runs code
- server/scripts/propose-plan.ts 1.5 KB runs code
- server/scripts/safe-plan.test.ts 10 KB runs code
- server/spec/mcp.md 241 KB
- server/spec/spec.md 5.4 KB
- server/src/auth-server.ts 19 KB runs code
- server/src/backup-export.ts 5.6 KB runs code
- server/src/cli.ts 1.7 KB runs code
- server/src/completed-archive.ts 3.4 KB runs code
- server/src/create-mcp-config.ts 1.4 KB runs code
- server/src/low-maintenance-analysis.ts 7.3 KB runs code
- server/src/oauth-refresh.ts 843 B runs code
- server/src/plan-proposer.ts 5.3 KB runs code
- server/src/safe-plan.ts 13 KB runs code
- server/src/setup.ts 5.2 KB runs code
- server/src/todo-index.ts 75 KB runs code
- server/src/todo-system-analysis.ts 7.8 KB runs code
- server/src/token-manager.ts 7.1 KB runs code
- server/test-api-exploration.js 5.7 KB runs code
- server/tsconfig.json 367 B
- server/tsup.config.ts 458 B runs code
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.
- 11d ago First seen · 206 lines · 67 tokens per session scan A 1eccc08e1c4a
microsoft-todo-safe-mcp is a skill published in the GitHub repository Saenai/microsoft-todo-safe-mcp (0 stars, last pushed 1mo ago), with no licence file. It adds 67 tokens to every session and 1,595 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.
Other skills, from other repositories
task-dependency-patterns
Task Management patterns with TaskCreate, TaskUpdate, TaskGet, TaskList tools. Decompose complex work into trackable tasks with dependency chains. Use when managing multi-step implementations, coordinating parallel work, or tracking completion status.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
cron-delete
Delete a scheduled cron task by name or ID.
task-queue-add
Add a one-shot task to the Custodian task queue.
handing-off-work
Hands off unfinished work with a closed-loop briefing of state, changed conditions, remaining scope, authority limits, and open evidence. Use when AI-agent, reviewer, verifier, releaser, or resumed-thread work transfers to a new owner. Do not use when the same owner continues uninterrupted with full context.
tracking-deficiencies
Keeps a standing register of known deficiencies so flaky tests, noisy alerts, unowned services, and recurring incidents get aged, owned, and fixed or formally risk-accepted instead of quietly normalized. Use when a known problem will outlive a single change. Do not use for a one-off lesson already closed inside a…