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 ahkedia/lyra-ai --skill job-outreach-gmailgit clone --depth 1 https://github.com/ahkedia/lyra-aiWrote 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/ahkedia/lyra-ai/job-outreach-gmail)<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/job-outreach-gmail"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/job-outreach-gmail/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/ahkedia/lyra-ai/job-outreach-gmail"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/job-outreach-gmail.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 | $0.00000 | $0.01318 |
| Opus 5 | $0.00000 | $0.00659 |
| Sonnet 5 | $0.00000 | $0.00264 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
job-outreach-gmail 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 11d 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.
Job / outreach → Gmail draft (Personal Wiki)
When this applies
Akash asks for an outreach message, cover letter, or Gmail draft tied to a job, a named contact, or former colleague context. The Tier-0 pipeline pulls Personal Wiki (Voice Canon + career pages) and writes Gmail drafts via himalaya — it does not rely on the chat model to "find" the wiki by name.
Session grounding — MANDATORY before every job turn
Before drafting, re-ground. Do not trust prior-turn state to still be in your context. On every turn in a job/outreach thread:
- Read
MEMORY.md→ Operator Facts (email, GitHub, location, CV location). Never re-ask any of these. - Query Personal Wiki (
database_id 33d78008-9100-8183-850d-e7677ac46b63) for:- Voice Canon (filter
Type = Voice Canon) — always - Career pages relevant to the target (filter
Type = Career, orDomain = [target's domain])
- Voice Canon (filter
- Re-read the in-thread context — any metrics, company details, or contact notes Akash already gave you. Carry them forward; never ask him to repeat.
If you skip step 1 or 2, you will re-ask stable facts and he will escalate — this is the #1 failure mode of this skill.
Anti-patterns (all observed in production; all forbidden)
- ❌ "I need your current phone number / Gmail / GitHub" → these are in
MEMORY.mdOperator Facts. Ask only if genuinely missing, and name the single missing field. - ❌ "Path to the AI-Akash PDF" → CV/resume is in Personal Wiki (
Type = CareerorType = CV). Query, don't ask for filesystem paths. - ❌ "I don't see a Personal Wiki database" / "listing databases in Lyra Hub" → wiki access is ID-based, not search-based. Query
33d78008-…. - ❌ "I'm working partially blind" while in-thread context has the metrics/company/role already — reread the thread.
- ❌ Re-asking a metric Akash already typed this session (e.g. "400% exposure lift") — carry it forward.
- ❌ Drafting without fetching Voice Canon — output will drift to generic voice.
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.
- 11d ago First seen · 88 lines · 0 tokens per session scan A f87ed41d0d0e
job-outreach-gmail is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 23d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,318 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 2026-08-31.
Other skills, from other repositories
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
rich-post
Send a Telegram rich-media post to ANOTHER allowlisted chat via the bot (Bot API 10.1 sendRichMessage) - text, inline images, tables, headings, lists, quotes, collapsible blocks, formulas, collages/slideshows ALL in one message bubble. Use when the owner asks to post somewhere other than the current conversation (the…
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
memory-processor
Iva's daily-memory processor. Reads the day's two-sided transcript (daily/YYYY-MM-DD.md), distills noteworthy entities / decisions / ideas into typed autograph cards, links them into the graph, and produces a daily-summary card (topics + MOC) that navigates down to the raw transcript and up to the week. Model-agnostic…
agent-browser
A command-line browser for interactive websites and web apps. It can open pages, inspect clickable elements, fill forms, click buttons, take screenshots, sign in, and read pages whose content is loaded by JavaScript.
update-recovery
A procedure for recovering custom changes after an Iva software update creates conflicts between the old and new versions.