pa

pa is a skill for Claude Code from ikenga-hq/ikenga-pkgs. It costs 132 tokens per session (1,091 once invoked), scanned A, original, Apache-2.0.

A personal-assistant dispatch skill for morning briefings, inbox and task triage, and approved send-queue actions. Triage means sorting incoming items and preparing decisions for review.

In plain words
What is it for?
Use it for daily or weekly briefings, sorting inbox and task items, and dispatching approved queued messages.
Why use it?
It brings information from tasks, calendars, email, and agent runs into focused briefings and keeps potentially consequential actions behind approval.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for daily or weekly briefings, sorting inbox and task items, and dispatching approved queued messages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ikenga-hq/ikenga-pkgs/pa
Install

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.

Any agent
npx skills add ikenga-hq/ikenga-pkgs --skill pa
Clone the repo
git clone --depth 1 https://github.com/ikenga-hq/ikenga-pkgs

Made for: Claude Code.

Wrote 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.

agentmods badge for pa

README.md
[![agentmods](https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/pa/github.svg)](https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/pa)
Your own site
<a href="https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/pa"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/pa/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.

agentmods 80×15 button for pa

Your own site · 80×15
<a href="https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/pa"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/pa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00132 $0.01091
Opus 5 $0.00066 $0.00545
Sonnet 5 $0.00026 $0.00218
Haiku 4.5 $0.00013 $0.00109

Measured 9d ago against content hash 3f995ce5c90a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pa 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 9d 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.

packages/skills/pa/skills/pa/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pa — dispatch-only PA surface

This file is a router. Each action lives in its own file under actions/; load on demand. The state contract (which ikenga.db tables are touched, read-vs-write boundary, dispatch-only scope) is in lib/state.md — read it before building any action.

skill-core note: depends_on: ['skill-core'] is declared above. skill-core is not yet packaged (Phase 3+). skill-pa declares the dependency edge now (per the G-04 contract and the lint spec in 06-skill-action-contract.md §5) so the graph is correct from day one; the dependency resolves when skill-core ships. Per the lint, no other target is legal.


Purpose (one line)

Dispatch morning briefing, inbox triage, task triage, and queued sends — reading ikenga.db state, never owning CRUD.


Dispatch actions

Action File Mode One-liner
briefing actions/briefing.md streaming Compile a morning/EOD/weekly briefing from tasks, calendar, email, and agent-run state.
triage actions/triage.md approve Triage unhandled inbox items (email + task queue) into buckets; produce draft decisions for operator approval before any write.
send actions/send.md confirm Dispatch approved items from the email-drafts queue; operator confirms the send-list before any delivery commit.
setup actions/setup.md streaming Configure skill-pa for the current project (inbox labels, triage buckets, send policy). Writes .atelier/skill-pa/manifest.json.

All four actions conform to the locked ActionFrontmatter Zod schema in plans/atelier/drafts/action-frontmatter.ts. Action bodies land in WP-12.


Routing

If the user says… Load Then
"morning briefing", "EOD summary", "weekly digest", "brief me" actions/briefing.md Compile from tasks + calendar_events + email_messages + agent_reports; stream to dock
"triage my inbox", "triage tasks", "what needs attention" actions/triage.md Read email_messages + tasks + delegations; produce triage decisions; pause for operator approval
"send queue", "dispatch drafts", "send approved emails" actions/send.md Read email_drafts where status = 'approved'; surface send-list; pause for operator approval
"setup PA", "configure skill-pa" actions/setup.md ai_infer or interview mode; writes .atelier/skill-pa/manifest.json

Read the full file on GitHub · 91 lines

Files

What ships with it

8 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.

Changes

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.

  1. 9d ago First seen · 91 lines · 132 tokens per session scan A 3f995ce5c90a

Subscribe to this mod's changes

pa is a skill published in the GitHub repository ikenga-hq/ikenga-pkgs (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 132 tokens to every session and 1,091 once invoked, about $0.0007 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.