Borrowing it
Nothing to install: this file belongs to s-morgan-jeffries/omnifocus-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/s-morgan-jeffries/omnifocus-mcp/main/.claude/skills/applescript-omnifocus/SKILL.mdgit clone --depth 1 https://github.com/s-morgan-jeffries/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/s-morgan-jeffries/omnifocus-mcp/applescript-omnifocus)<a href="https://agentmods.dev/skills/s-morgan-jeffries/omnifocus-mcp/applescript-omnifocus"><img src="https://agentmods.dev/badge/skills/s-morgan-jeffries/omnifocus-mcp/applescript-omnifocus/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/s-morgan-jeffries/omnifocus-mcp/applescript-omnifocus"><img src="https://agentmods.dev/badge/skills/s-morgan-jeffries/omnifocus-mcp/applescript-omnifocus.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 | $0.00069 | $0.01631 |
| Opus 5.5 | $0.00028 | $0.00652 |
| Sonnet 5.5 | $0.00014 | $0.00326 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
applescript-omnifocus scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
This is more reliable than catching `subprocess.CalledProcessError`, which doesn't always contain useful error messages from OmniFocus. How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AppleScript + OmniFocus Patterns
This skill covers the hard-won knowledge about scripting OmniFocus via AppleScript. These are not obvious from documentation and have caused real bugs in this project.
Critical: Variable Naming Conflicts
OmniFocus AppleScript has a dangerous quirk: if you use a variable name that matches an OmniFocus property, AppleScript silently reads the property instead of your variable.
Bug-causing names (NEVER use as variables):
name, note, status, flagged, completed, sequential, due date, defer date, estimated minutes, repetition rule, repetition method
Safe naming pattern: Always prefix with the entity type:
-- BAD: "name" collides with OmniFocus property
set name to "My Task"
set name of theTask to name -- reads property of theTask, not your variable!
-- GOOD: prefixed variable name
set taskName to "My Task"
set name of theTask to taskName -- works correctly
Real bug from this project: A variable called status inside a tell task block caused OmniFocus to read the task's status property instead of the variable value, producing silent data corruption. The elifintervalDays typo story: unit tests passed because they mocked AppleScript, but integration tests against real OmniFocus caught the variable collision. This is why integration tests exist.
Rich Text Notes Limitation
OmniFocus stores notes as rich text internally. The AppleScript API exposes this inconsistently:
- Reading:
note of taskreturns plain text (stripped of formatting) - Writing:
set note of task to "text"replaces the entire note with plain text, destroying any rich text formatting
There is no workaround. You cannot preserve rich text through the AppleScript API. Document this to users and warn when overwriting notes.
Recurring Task Completion
Two ways to complete a task — only one handles recurrence correctly:
-- CORRECT: Creates next occurrence for recurring tasks
mark complete theTask
-- WRONG: Just marks this instance done, no next occurrence spawned
set completed of theTask to true
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.
- 1mo ago First seen · 165 lines · 69 tokens per session scan A 628c4b016763
applescript-omnifocus is a skill published in the GitHub repository s-morgan-jeffries/omnifocus-mcp (8 stars, last pushed 5mo ago), licensed MIT. It adds 69 tokens to every session and 1,631 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
report-issue
File a bug or feature request against this repository (cyanheads/git-mcp-server) using the gh CLI. Use for tool logic bugs, git provider misbehavior, transport issues, auth/config problems, or new feature proposals.
build-flow
Create or change a Keboola flow that runs extractors, transformations and writers in order, optionally on a schedule. Use when the user wants to orchestrate, chain or schedule existing Keboola configurations.
reviewing-sla-definitions
Reviewing ServiceNow SLA, OLA and underpinning-contract definitions and how they perform: breach rates per definition, overlapping or duplicated definitions on the same table and target, and definitions that never attach. Use when the user asks about SLA breaches by definition, too many SLAs, duplicate or conflicting…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
papi-plan
Invoke when starting a new PAPI cycle. Covers plan generation, board management, and cycle scoping rules.
papi-idea
Invoke when submitting backlog ideas, registering docs, or filing research. Covers idea pipeline and doc registry conventions.