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 ikenga-hq/ikenga-pkgs --skill mailgit clone --depth 1 https://github.com/ikenga-hq/ikenga-pkgsWrote 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/ikenga-hq/ikenga-pkgs/mail)<a href="https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/mail"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/mail/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/ikenga-hq/ikenga-pkgs/mail"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/mail.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 | $0.00160 | $0.01037 |
| Opus 5 | $0.00080 | $0.00518 |
| Sonnet 5 | $0.00032 | $0.00207 |
| Haiku 4.5 | $0.00016 | $0.00104 |
Grade A, and why
mail 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 8d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mail — dispatch-only mail 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-coreis onikenga-pkgsmain (WP-15 done). skill-mail declares the dependency edge here (per the G-04 contract and the lint spec in06-skill-action-contract.md§5) so the graph is correct from day one. The shell resolver installs theskill-coreclosure at enable time.
Purpose (one line)
Triage the inbox, draft replies for operator approval, and configure the mail
skill per project — reading ikenga.db state, never owning CRUD.
Dispatch actions
| Action | File | Mode | One-liner |
|---|---|---|---|
setup |
actions/setup.md |
streaming |
Configure inbox source + send identity. Writes .atelier/skill-mail/manifest.json. |
triage-inbox |
actions/triage-inbox.md |
approve |
Triage untriaged email_messages into buckets; draft decisions for operator approval. Zero writes. |
draft-reply |
actions/draft-reply.md |
confirm |
Draft a reply for the selected thread into the quick-reply surface. The email_replies write happens via the mail pkg on send. |
All three actions conform to the locked ActionFrontmatter Zod schema in
plans/atelier/drafts/action-frontmatter.ts.
Routing
| If the user says… | Load | Then |
|---|---|---|
| "triage my inbox", "what emails need attention", "triage email" | actions/triage-inbox.md |
Read email_messages where triage_category IS NULL; bucket + draft decisions; pause for operator approval |
| "draft a reply to this thread", "reply to [sender]", "draft reply" | actions/draft-reply.md |
Read thread context from email_messages + contacts; draft reply; insert into quick-reply surface; pause for operator confirm |
| "setup mail", "configure skill-mail", "set up my email" | actions/setup.md |
ai_infer or interview mode; writes .atelier/skill-mail/manifest.json |
What ships with it
5 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.
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.
- 8d ago First seen · 88 lines · 160 tokens per session scan A 1cb5583fb31c
mail is a skill published in the GitHub repository ikenga-hq/ikenga-pkgs (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 160 tokens to every session and 1,037 once invoked, about $0.0008 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.