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/runbear-io/aweek/setupnpx skills add runbear-io/aweek --skill setupgit clone --depth 1 https://github.com/runbear-io/aweekWhat 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 | $0.00031 | $0.06403 |
| Opus 5 | $0.00015 | $0.03202 |
| Sonnet 5 | $0.00006 | $0.01281 |
| Haiku 4.5 | $0.00003 | $0.00640 |
Grade A, and why
setup 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 — 573 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aweek:setup
Bootstrap a project for the aweek agent scheduler. Most users never need to
run this manually — every other skill auto-bootstraps the project when it
first runs. Use /aweek:setup when you want to explicitly control the
heartbeat installation, or to reset a sticky heartbeat decision so other
skills re-prompt.
It prepares the filesystem layout and (optionally) installs the 10-minute heartbeat that drives agent execution.
The heartbeat is installed via the platform's native scheduler:
- macOS → a launchd user agent at
~/Library/LaunchAgents/io.aweek.heartbeat.<hash>.plist. This is the default on darwin because cron jobs can't access the macOS Keychain, and Claude Code's subscription OAuth tokens live there — the launchd user agent runs inside your aqua session, so Keychain access works exactly like from Terminal. - Linux / other POSIX → a crontab entry (
*/10 * * * *). If a legacy crontab entry exists on a macOS machine from an earlier aweek version, it is migrated automatically the next time/aweek:setupinstalls the launchd agent.
Slash-command discovery is handled by the Claude Code plugin system — this
skill does not copy markdown into .claude/commands/. Users who installed
aweek via /plugin install aweek@… already have every /aweek:* command
available.
This skill is a thin UX wrapper on top of src/skills/setup.ts. All filesystem
mutations, crontab writes, and idempotency checks live in that module — do
not edit .aweek/ or the user's crontab directly.
Arguments
/aweek:setup is interactive and takes no positional arguments. The underlying
runInit() function in src/skills/setup.ts accepts the following optional
options for advanced / non-interactive invocation:
| Option | Type | Default | Description |
|---|---|---|---|
projectDir |
string | process.cwd() |
Project root where .aweek/ will be created |
dataDir |
string | .aweek/agents |
Path (relative to projectDir) for the agent data directory |
installHeartbeat |
boolean | false |
Whether to install the 10-minute heartbeat crontab entry (destructive — requires confirmation) |
heartbeatSchedule |
string | */10 * * * * |
Cron schedule used when installHeartbeat is true |
confirmed |
boolean | false |
Must be true to allow destructive operations (crontab install, overwriting an existing data dir) |
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 · 573 lines · 31 tokens per session scan A f15049330b90
setup is a skill published in the GitHub repository runbear-io/aweek (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 6,403 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…