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 phd-peter/codex-omnifocus-mcp --skill codex-omnifocusgit clone --depth 1 https://github.com/phd-peter/codex-omnifocus-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/phd-peter/codex-omnifocus-mcp/codex-omnifocus)<a href="https://agentmods.dev/skills/phd-peter/codex-omnifocus-mcp/codex-omnifocus"><img src="https://agentmods.dev/badge/skills/phd-peter/codex-omnifocus-mcp/codex-omnifocus.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 | $0.00049 | $0.00372 |
| Opus 5 | $0.00024 | $0.00186 |
| Sonnet 5 | $0.00010 | $0.00074 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
codex-omnifocus 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 7d 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.
What it actually says
Codex OmniFocus
Use the codex-omnifocus MCP server for OmniFocus task and project work.
Workflow
- Look first with
query_omnifocus,filter_tasks,get_task_by_id,get_inbox_tasks,get_forecast_tasks, orget_custom_perspective_tasks. - Prefer IDs for edits, moves, removals, and duplicate-prone names.
- Use
edit_itemormove_taskfor existing tasks. Useadd_omnifocus_taskonly for genuinely new tasks. - Use
batch_add_itemsandbatch_remove_itemsfor multi-item changes. - Use
list_tagsbefore assigning unfamiliar tags; usecreate_tagwhen a missing tag should exist.
Write Policy
Full agent writes are enabled. Do not add an extra confirmation step unless the user asks for one or the request is ambiguous.
The server writes audit JSONL records for write tools under CODEX_OMNIFOCUS_AUDIT_DIR or ~/.codex/codex-omnifocus-mcp/audit.
Tool Selection
- Use
query_omnifocusfor compact task/project/folder lookups and counts. - Use
filter_tasksfor broad custom task views. - Use
get_custom_perspective_tasksfor OmniFocus custom perspectives. - Use
get_tasks_by_tagfor tag-filtered views. - Use
dump_databaseonly when a full database snapshot is truly needed.
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.
- 7d ago First seen · 31 lines · 49 tokens per session scan A 4e22aec872e9
codex-omnifocus is a skill published in the GitHub repository phd-peter/codex-omnifocus-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 372 once invoked, about $0.0002 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
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks CoWork-OSS to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
usecase-chief-of-staff-briefing
Build a morning/evening executive brief from calendar, inbox, tasks, and optional ops signals.
usecase-household-capture
Turn a messy household message into Notion tasks + optional reminders.
usecase-family-digest
Draft a daily digest based on calendar + tasks. Stops before sending.
touch-grass
Configure local cat-GIF break reminders while using Codex or Claude Code. Use when the user asks to change a reminder cadence or clock time, enable or disable break types, set bedtime or quiet hours, add a custom reminder or cat, snooze reminders, or see personalization examples.
wecomcli-todo
A tool for managing to-do items in WeCom, the workplace messaging and collaboration app used by many Chinese companies. It handles existing WeCom tasks and their titles, descriptions, people, status, and deadlines.