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 metraton/gaia --skill gmail-triagegit clone --depth 1 https://github.com/metraton/gaiaWrote 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/metraton/gaia/gmail-triage)<a href="https://agentmods.dev/skills/metraton/gaia/gmail-triage"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gmail-triage/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/metraton/gaia/gmail-triage"><img src="https://agentmods.dev/badge/skills/metraton/gaia/gmail-triage.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 | $0.00024 | $0.02652 |
| Opus 5 | $0.00012 | $0.01326 |
| Sonnet 5 | $0.00005 | $0.00530 |
| Haiku 4.5 | $0.00002 | $0.00265 |
Grade A, and why
gmail-triage 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.
How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gmail Triage
Interactive GTD-inspired state machine for Gmail. Gaia analyzes threads, proposes transitions. User decides. Gaia executes. This is the PROCESS layer; it depends on gmail-policy for every rule -- label definitions, security tiers, the interpretation of a review trigger (Intent Classification), and the Autonomous Action Boundary that decides what may run without approval. That dependency holds in every mode, headless included: a security rule cannot live only in the process that obeys it.
State Labels
Five _gaia/* labels (defined in gmail-policy) — three durable active states, plus staging and soft-delete:
_gaia/action— user must act_gaia/waiting— user acted, awaiting reply_gaia/someday— interesting, no urgency_gaia/pending— staging (triage backlog)_gaia/trash— soft delete; never truly deleted
No _gaia/* label = processed/done.
Thread-Awareness Rule
Before presenting ANY labeled email, check the thread: message count, who sent last, when. This determines framing:
- "necesitas responder" (user is last)
- "esperando desde [date]" (user replied, waiting on them)
- "sin actividad hace 2 semanas — ¿hacer seguimiento?" (stale waiting)
These two sections are the state-machine expression of the Autonomous Action Boundary in gmail-policy — the boundary is the rule, these are its transitions.
Automatic Transitions (no confirmation needed)
- User replies to an
actionthread → move towaiting - New message arrives in a
waitingthread → move toaction
Transitions Requiring Confirmation
- Anything →
trashorsomeday - Clearing any label (marking done)
someday→action
Modes
Modes 1–5 open with a state summary before their specific work:
"Antes de empezar: N en action, N en waiting, N en someday." Flag action items stale >3 days.
0. Check ("chequea mi mail" / "¿algo nuevo?")
- Review
_gaia/action— present each item with thread framing. Did user already reply? Auto-apply →waiting(mechanical, reversible — no confirmation). - Review
_gaia/waiting— did the other party respond? Auto-apply →action(mechanical, reversible — no confirmation). Stale >1 week → flag. - Review
_gaia/someday— count only: "tienes 5 en someday." Detail only if asked. - Scan inbox for new signal — Financial (large amounts, bills, due dates), personal/important (housing, legal, health), expected reply arrived → propose
action. Interesting, no urgency → proposesomeday. - Summarize — overall inbox state in 2-3 sentences.
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.
- 9d ago First seen · 145 lines · 24 tokens per session scan A cfc9b88a06a6
gmail-triage is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 2,652 once invoked, about $0.0001 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
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
codex-result-handling
Internal contract for returning Codex companion output without alteration.
shipwrights-loop
Drive multiple Jira tickets sequentially through the /shipwrights-epic pipeline. Auto-picks the next ticket, watches the PR until merged, transitions Jira to shipped, repeats. Resumable across Claude Code sessions via .shipwrights/loop-state.json. Invoked as /shipwrights-loop [N] | --status | --abort.