gmail-watch

gmail-watch is a skill for Claude Code, Codex from Open-Curiosity/gini-agent. It costs 61 tokens per session (733 once invoked), scanned A, original, MIT.

A background service that checks Gmail watches for new matching messages and passes likely human-written matches to a shared reply-drafting process.

In plain words
What is it for?
Monitoring saved Gmail queries, spotting new messages, avoiding duplicates, and preparing reply drafts from the sender, subject, date, and snippet.
Why use it?
It removes the need to check several saved Gmail searches by hand and filters out automated messages and your own emails.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Monitoring saved Gmail queries, spotting new messages, avoiding duplicates, and preparing reply drafts from the sender, subject, date, and snippet.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/open-curiosity/gini-agent/gmail-watch
About the project

Gini Agent is a personal AI-agent runtime that manages conversations, runs, tasks, approvals, memory, skills, jobs, tools, traces, audit events, and runtime health across its clients. It is for an agent that can remember, learn from task outcomes, and operate through desktop or mobile interfaces with user controls. Catalogue add-ons extend the runtime with skills and instructions.

Open-Curiosity/gini-agent · 1,986 stars · on GitHub

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 Open-Curiosity/gini-agent --skill gmail-watch
Clone the repo
git clone --depth 1 https://github.com/Open-Curiosity/gini-agent

Made for: Claude Code, Codex.

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 gmail-watch

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-curiosity/gini-agent/gmail-watch.svg)](https://agentmods.dev/skills/open-curiosity/gini-agent/gmail-watch)
Your own site
<a href="https://agentmods.dev/skills/open-curiosity/gini-agent/gmail-watch"><img src="https://agentmods.dev/badge/skills/open-curiosity/gini-agent/gmail-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 27
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00061 $0.00733
Opus 5 $0.00030 $0.00367
Sonnet 5 $0.00012 $0.00147
Haiku 4.5 $0.00006 $0.00073

Measured 8d ago against content hash 9e6ee49df7ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gmail-watch 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/detect.test.ts, scripts/detect.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/google/gmail-watch/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gmail Watch

This skill ships the detection engine behind your email watches. It is not something you run by hand — when you create an email watch (email_watch tool, gini email add, or the settings UI), Gini adds it to ONE shared background job whose pre-run hook runs this skill's detect script on a schedule. All of your watches share that one job and one "Email watch" chat thread; the script decides which watches have new mail to draft a reply to.

What it does

Each time the shared watch job fires, detect runs headless (no model turn, no approval) and, for EACH of your watches:

  1. Checks the Google sign-in (once for the session). If signed out, every watch reports needs_auth and nothing is drafted — the watches stay active and recover the moment you re-authenticate.
  2. Lists new mail matching that watch's query via gws, bounded by a per-watch watermark so steady-state polling lists almost nothing.
  3. Drops automated senders (no-reply, mailer-daemon, notifications, …) and your own address — only real, human, new mail survives.
  4. Hands each surviving match (its sender / Subject / Date / snippet only — never the body), labeled by sender, to the drafting turn as quoted, untrusted data.

Each watch is independent: one sender's transient error marks only that watch and the others keep working. When nothing new matches across all your watches, the run ends with no model turn at all — the watches are silent until there is something to act on.

How a match becomes a reply

The detection floor reads only metadata. One drafting turn then handles all the matches for that tick in the shared thread: it reads each full message and composes a reply per email — each labeled by sender — through the google-gmail skill, posts the proposed replies for you to review, and sends only when you explicitly ask (which runs gws gmail +reply through the normal approval gate).

Stateful but pure

detect is a pure function of your watch list and the small per-watch cursors it is handed each run; it never writes to disk itself. Gini stores those cursors on the shared watch job and advances each only after a drafting turn is dispatched, so a match is never silently lost if delivery fails — it re-surfaces on the next run.

Read the full file on GitHub · 66 lines

Files

What ships with it

2 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. 8d ago First seen · 66 lines · 61 tokens per session scan A 9e6ee49df7ef

Subscribe to this mod's changes

gmail-watch is a skill published in the GitHub repository Open-Curiosity/gini-agent (1,986 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 733 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

clinical-reports

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation…

synthetic-sciences/openscience · 71 tokens

imaging-data-commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

synthetic-sciences/openscience · 62 tokens

clinical-decision-support

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading…

synthetic-sciences/openscience · 97 tokens

clinical-imaging

Clinical and physiological imaging analysis. Diffusion MRI ADC maps, micro-CT bone morphometry, hemodynamic parameter analysis, circadian rhythm cosinor analysis, ciliary beat frequency (FFT), and tissue deformation optical flow. For DICOM file handling use pydicom; for biosignals use neurokit2.

synthetic-sciences/openscience · 69 tokens

curated-bio-datasets

Guide to accessing curated biological datasets for computational biology. COSMIC cancer data, GTEx expression, GWAS catalog, GeneBass exome variants, BioGRID interactions, MSigDB gene sets, DisGeNET disease-gene associations, and GO ontology. For specific database APIs use individual database skills (cosmic-database…

synthetic-sciences/openscience · 79 tokens

gget

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST searches, AlphaFold structures, enrichment analysis. Best for interactive exploration, simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

synthetic-sciences/openscience · 66 tokens