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/mnott/pai/tasksnpx skills add mnott/PAI --skill tasksgit 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 | $0.00079 | $0.01351 |
| Opus 5 | $0.00039 | $0.00675 |
| Sonnet 5 | $0.00016 | $0.00270 |
| Haiku 4.5 | $0.00008 | $0.00135 |
Grade C, and why
Tasks scanned grade C 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 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
An explicit label that matches nothing does **not** fall through to the container. That is deliberate: the user meant to route it somewhere specific, and quietly sending it elsewhere would be worse than not routing it at How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasks Skill
USE WHEN user says 'morning routine', 'what needs doing', 'run the routine', 'check my tasks', 'dispatch tasks', 'file a finding', 'add this to todoist', 'what did we find', OR /tasks.
What This Skill Does
The task bus is shared state that outlives any one session. Session-local work stays in each project's Notes/TODO.md; the bus carries work that is broader than one session — findings discovered sideways, and work that belongs to a project other than the one you are sitting in.
Three workflows: morning routine, file a finding, triage.
Pre-Action Check (MANDATORY)
Run this before anything else. If it reports the bus is not configured, say so and stop — do not attempt to work around it by calling the Todoist MCP directly.
pai task list --limit 1
If it prints "Task bus is not configured", tell the user to run pai setup and complete the Task Bus step. Nothing else in this skill will work.
Workflow 1 — Morning Routine
Trigger: "morning routine", "what needs doing", "run the routine".
Step 1 — Read what is open
pai task list --today
This shows tasks due today or overdue. Drop --today for everything open.
Step 2 — Report before acting
Group what you found by owner and present it. Lead with anything overdue or p1.
Do not dispatch silently. The user should see the list before sessions start receiving work.
Step 3 — Dispatch
pai task dispatch --today --dry-run # always preview first
pai task dispatch --today # then, once the user approves
Outcomes and what each means:
| Symbol | Outcome | Meaning |
|---|---|---|
→ |
delivered | Sent to an already-running session |
+ |
spawned | No session was running; one was launched, then sent to |
? |
unrouted | No owner resolved — the task stays in the findings inbox |
! |
unlaunchable | An owner resolved but it has no PAI alias to launch |
· |
skipped | Auto-dispatch is off, or no transport — reported only |
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 · 127 lines · 79 tokens per session scan C 696e1f6bd452
Tasks is a skill published in the GitHub repository mnott/PAI (45 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 1,351 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…