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 skills/basecamp/hey-cli/heynpx skills add basecamp/hey-cli --skill heygit clone --depth 1 https://github.com/basecamp/hey-cliWhat 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 | $0.00049 | $0.10873 |
| Opus 5 | $0.00024 | $0.05437 |
| Sonnet 5 | $0.00010 | $0.02175 |
| Haiku 4.5 | $0.00005 | $0.01087 |
Grade A, and why
hey 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 2d 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 — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hey - HEY Email Workflow Command
CLI for HEY: mailboxes, labels, collections, email threads, contacts, replies, compose, calendars, todos, habits, time tracking, and journal entries.
Agent Invariants
MUST follow these rules:
- Choose the right structured output — use
--jq '<expression>'to filter or extract fields and--jsonfor the full response. Never pipe to an externaljq;--jqis built in and implies--json. - Authentication required for all data commands — run
hey auth loginfirst - HTML output is available via
--htmlfor commands that return HTML content - Linked mail accounts share one login — use
hey account list --json, then--account <id|all>when a task must target one account - Local HEY configuration requires human trust — never run
hey config trust-localwithout the user's explicit approval
Output Filtering
--jq filters the full JSON success envelope, so result data is under .data. String results print as plain text; objects and arrays print as formatted JSON. Use --quiet --jq when the expression should run against result data directly. Errors retain their complete structured envelope. Commands with dedicated raw output (auth token, completion, skill, tui, and --version) reject --jq.
hey box list --jq '.data[] | {id, name}'
hey search "quarterly planning" --jq '.data[].id'
hey box list --quiet --jq '.[].name'
An empty result is an empty array rather than null, so .data[] is safe to run against a
listing that found nothing.
For the two commonest shapes there is no need for an expression at all: --ids-only prints
one ID per line and --count prints a bare number, both on stdout with any pagination
notice on stderr. Both need list data, so they work on hey box list, hey box view,
hey label list, hey label view, hey collection list, hey collection view, hey workflow list,
hey workflow view, hey clip list, hey snippet list, hey draft list, hey search,
hey contact list, hey screener list, hey screener history, hey calendar list,
hey event list, hey todo list, hey habit list, hey timetrack list, hey journal list and
hey attachment list. On hey box view they count and list its postings, not the box itself.
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.
- 2d ago First seen · 771 lines · 49 tokens per session scan A 2710f348c319
hey is a skill published in the GitHub repository basecamp/hey-cli (239 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 10,873 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…