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 agentmods add instructions/veliovgroup/mail-time/claude-mdgit clone --depth 1 https://github.com/veliovgroup/mail-timeWrote 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/instructions/veliovgroup/mail-time/claude-md)<a href="https://agentmods.dev/instructions/veliovgroup/mail-time/claude-md"><img src="https://agentmods.dev/badge/instructions/veliovgroup/mail-time/claude-md.svg" alt="Measured on agentmods" 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 | $0.01420 | $0.01420 |
| Opus 5 | $0.00710 | $0.00710 |
| Sonnet 5 | $0.00284 | $0.00284 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
mail-time CLAUDE.md 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file is Claude Code's working brief for the mail-time repository. It complements AGENTS.md (general agent guidelines) and skills/mail-time/SKILL.md (the distributable user-facing skill).
What this repo is
mail-time is an NPM package that queues and sends emails (via nodemailer transports) across horizontally scaled Node.js / Bun apps. It uses Mongo / Redis / Postgres (or a custom adapter) for queue storage and the josk library for cluster-aware scheduling.
Where to look first
- Editing core behavior? →
index.js. Everything else (CJS bundle, types) is regenerated from it. - Adding / fixing an adapter? →
adapters/<store>.jsplusadapters/blank-example.jsas scaffold +docs/queue-api.mdfor the contract. - Tuning a preset / adding one? →
presets.js. Test intest/jest/presets.test.js. The re-export fromindex.jsis already wired. - Testing? →
test/jest/*.test.jsis the fast unit suite (no live DB).test/npm-*.jsis the integration suite that needsREDIS_URL/MONGO_URL/PG_URL. - TS types? → JSDoc lives in
index.js,presets.js, andadapters/*.js. The .d.ts is generated. To strip private members,scripts/strip-internal-dts.mjsruns as part ofprepublishOnly. - User docs? →
README.md(public),docs/{multi-instance,dedicated-mail-host,tuning,queue-api,meteor,migration-v3-v4}.md(dive-in examples), andskills/mail-time/SKILL.md(Claude-facing). - AI instructions and guidelines? →
AGENTS.mdand this fileCLAUDE.md(Claude-facing).
Mental model for changes
- Read the JoSk skill (
/joskor~/.claude/skills/josk/) when changing scheduler-related code. MailTime is a thin layer over JoSk for an email-shaped workload — most "should this happen?" questions resolve through JoSk's contract. - Public methods on
MailTimeand the three queues are stable contract. Internal helpers (___send,___compileMailOpts,__getKey, etc.) are explicitly marked internal and stripped from .d.ts — they're free to change. - The only runtime dep is
josk. Don't add another without a written reason in the PR description.
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.
- 4d ago First seen · 58 lines · 1,420 tokens per session scan A 112877096dc1
mail-time CLAUDE.md is an instructions file published in the GitHub repository veliovgroup/mail-time (143 stars, last pushed 22d ago), licensed BSD-3-Clause. It adds 1,420 tokens to every session, about $0.0071 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.
Other instructions, from other repositories
js-bson AGENTS.md
Instructions for mongodb/js-bson, covering agents.md, project overview, commands, benchmarks and structure.
js-bson CLAUDE.md
Instructions for mongodb/js-bson, a project described as: BSON Parser for node and browser.
kavo CLAUDE.md
Claude Code instructions for kavo-labs/kavo, covering claude.md, what kavo is, commands, architecture and the request pipeline (the spine).
swarmcode CLAUDE.md
Instructions for spranab/swarmcode, covering swarmcode, architecture, key design, running and environment.
mcp-database CLAUDE.md
Claude Code instructions for DiegoBulhoes/mcp-database, covering claude.md, commands, architecture, invariants (do not weaken) and adding or changing a tool.
MCP-DB AGENTS.md
AGENTS.md instructions for phatngoit/MCP-DB, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.