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 agentmods add skills/zapier/connectors/microsoft-todonpx skills add zapier/connectors --skill microsoft-todogit clone --depth 1 https://github.com/zapier/connectorsWrote 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/zapier/connectors/microsoft-todo)<a href="https://agentmods.dev/skills/zapier/connectors/microsoft-todo"><img src="https://agentmods.dev/badge/skills/zapier/connectors/microsoft-todo.svg" alt="Measured on agentmods" 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 | $0.00099 | $0.03203 |
| Opus 5 | $0.00049 | $0.01602 |
| Sonnet 5 | $0.00020 | $0.00641 |
| Haiku 4.5 | $0.00010 | $0.00320 |
Grade A, and why
microsoft-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 6d 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
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
54 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.
- .claude-plugin/plugin.json 1.0 KB
- .mcp.json 144 B
- CHANGELOG.md 1.3 KB
- cli.js 7.3 KB runs code
- cli.ts 141 B runs code
- connections.ts 220 B runs code
- evals/evals.json 18 KB
- evals/results.md 3.0 KB
- index.ts 2.2 KB runs code
- lib/microsoft-todo.ts 11 KB runs code
- LICENSE 3.8 KB
- NOTICE 484 B
- package.json 1.4 KB
- README.md 8.6 KB
- references/microsoft-todo-api-gotchas.md 10 KB
- references/use-as-cli.md 2.8 KB
- references/use-as-mcp.md 2.6 KB
- references/use-as-recipe.md 10 KB
- references/use-as-sdk.md 1.3 KB
- references/use-with-zapier.md 6.3 KB
- references/use-without-zapier.md 4.5 KB
- scripts/completeTask.ts 1.8 KB runs code
- scripts/createChecklistItem.ts 1.9 KB runs code
- scripts/createList.ts 1.0 KB runs code
- scripts/createTask.ts 4.0 KB runs code
- scripts/deleteChecklistItem.ts 1.8 KB runs code
- scripts/deleteList.ts 1.2 KB runs code
- scripts/deleteTask.ts 1.6 KB runs code
- scripts/findTask.ts 3.0 KB runs code
- scripts/getList.ts 1.0 KB runs code
- scripts/getTask.ts 1.4 KB runs code
- scripts/listChecklistItems.ts 2.5 KB runs code
- scripts/listLists.ts 1.9 KB runs code
- scripts/listTasks.ts 2.6 KB runs code
- scripts/updateChecklistItem.ts 2.2 KB runs code
- scripts/updateList.ts 1.3 KB runs code
- scripts/updateTask.ts 4.5 KB runs code
- tests/completeTask.test.ts 2.1 KB runs code
- tests/createChecklistItem.test.ts 2.7 KB runs code
- tests/createList.test.ts 1.9 KB runs code
- tests/createTask.test.ts 2.8 KB runs code
- tests/deleteChecklistItem.test.ts 1.9 KB runs code
- tests/deleteList.test.ts 1.8 KB runs code
- tests/deleteTask.test.ts 1.8 KB runs code
- tests/findTask.test.ts 3.3 KB runs code
- tests/getList.test.ts 2.4 KB runs code
- tests/getTask.test.ts 2.6 KB runs code
- tests/listChecklistItems.test.ts 2.9 KB runs code
- tests/listLists.test.ts 3.3 KB runs code
- tests/listTasks.test.ts 3.0 KB runs code
- tests/updateChecklistItem.test.ts 2.6 KB runs code
- tests/updateList.test.ts 2.0 KB runs code
- tests/updateTask.test.ts 2.8 KB runs code
- tsup.config.ts 1.9 KB 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.
- 6d ago First seen · 143 lines · 99 tokens per session scan A 896c3c451d82
microsoft-todo is a skill published in the GitHub repository zapier/connectors (165 stars, last pushed 11d ago), with no licence file. It adds 99 tokens to every session and 3,203 once invoked, about $0.0005 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.
Other skills, from other repositories
cocoplus-on
Activate Full Assist Mode — enables all CocoPlus features simultaneously: Memory Engine, Environment Inspector, Safety Gate (normal), Code Quality Advisor, Context Mode, and CocoMeter. Also triggers a background environment scan. Idempotent.
cocoplus-off
Deactivate Full Assist Mode — removes all CocoPlus feature flags. Data files (memory, meter history, grove patterns) are preserved. Idempotent.
wisdom-forget
Remove a must-keep CocoWisdom entry with rationale. Usage: $wisdom forget --id --rationale " ".
afrexai-career-accelerator
Complete career acceleration system — from self-assessment to offer negotiation. Covers career strategy, job search operations, resume/CV optimization, interview preparation, salary negotiation, career transitions, and long-term growth planning. Works for any role, any level, any industry.
0codekit
0codekit integration. Manage Workspaces. Use when the user wants to interact with 0codekit data.
13-Day Sprint Method
Productivity system based on Maya calendar with 13 natural tones for project management and personal development.