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 commands/mnott/pai/taskgit clone --depth 1 https://github.com/mnott/PAIWhat 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 | $0.00000 | $0.01571 |
| Opus 5 | $0.00000 | $0.00785 |
| Sonnet 5 | $0.00000 | $0.00314 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
task 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pai task
Task bus: list, add, dispatch, and complete cross-session work
Aliases: tasks
Synopsis
pai task <subcommand> [options]
Subcommands
| Command | Description |
|---|---|
pai task projects |
Show which sessions can be given work from the tracker, and create the missing projects |
pai task list |
List open tasks on the bus |
pai task add <title> |
File a task onto the bus |
pai task dispatch |
Hand open tasks to the PAI sessions that own them |
pai task poll |
One scheduler tick: dispatch what is due, check what is running, report |
pai task schedule |
Install, remove or inspect the launchd agent that ticks the scheduler |
pai task config |
View or change task bus settings without running the full setup wizard |
pai task archive <id> |
Save a task's discussion into the owning project's notes, without completing it |
pai task done <id> |
Mark a task complete on the tracker, keeping its discussion |
pai task projects
Show which sessions can be given work from the tracker, and create the missing projects
Options
| Option | Description | Default |
|---|---|---|
--create <names...> |
Create tracker projects for these session names | |
--create-all |
Create a project for every session that has none |
pai task list
List open tasks on the bus
Options
| Option | Description | Default |
|---|---|---|
--owner <project> |
Only tasks owned by this PAI project | |
--due <date> |
Only tasks due on or before this ISO date | |
--today |
Shorthand for --due | |
--routed |
Hide tasks with no resolved owner | |
--limit <n> |
Maximum tasks to show |
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.
- 2d ago First seen · 187 lines · 0 tokens per session scan A a7803ddf359f
task is a command published in the GitHub repository mnott/PAI (45 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,571 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.