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/run-oncenpx skills add runbear-io/aweek --skill run-oncegit clone --depth 1 https://github.com/runbear-io/aweekWrote 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/runbear-io/aweek/run-once)<a href="https://agentmods.dev/skills/runbear-io/aweek/run-once"><img src="https://agentmods.dev/badge/skills/runbear-io/aweek/run-once.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 5.1 | $0.00039 | $0.01363 |
| Opus 5 | $0.00019 | $0.00681 |
| Sonnet 5 | $0.00008 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
run-once 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 6d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aweek:run-once
Manually dispatch an ad-hoc, one-shot task to an aweek agent. The task goes through the exact same execution path the hourly heartbeat uses — per-agent heartbeat lock, per-agent .env, executeSessionWithTracking with dangerouslySkipPermissions, and a full activity-log / execution-log entry — but the task itself is ephemeral: it is never written to the weekly plan and does not consume a weekly-plan slot.
Use this to debug a single agent without waiting for the next tick, or to probe an agent that is currently budget-paused (the skill deliberately force-runs through config.paused).
What this skill does NOT do
- Does not add the task to the weekly plan.
- Does not pause, resume, or top-up the agent (use
/aweek:managefor lifecycle ops). - Does not bypass the per-agent heartbeat lock — a manual run will wait for, or skip, any in-flight tick.
- Does not skip the destructive-operation confirmation gate.
Destructive operation policy
Running an ad-hoc task costs tokens (counted against the agent's weekly budget exactly like a scheduled tick) and can force-run through a pause. Per project policy, this requires an explicit AskUserQuestion confirmation before confirmed: true is set. Never pass confirmed: true without collecting the user's "yes".
Instructions
You MUST follow this exact workflow when this skill is invoked. All persistence goes through src/skills/run-once.js via the dispatcher — never spawn Claude Code CLI sessions directly.
Step 1: Pick the target agent
List all agents so the user can pick one:
echo '{"dataDir":".aweek/agents"}' \
| aweek exec agent-helpers listAllAgents --input-json -
Project each entry to { id, name: identity?.name, paused: budget?.paused } for display. If the roster is empty, tell the user to run /aweek:hire first and stop.
Ask the user via AskUserQuestion: "Which agent should run the ad-hoc task?" — pass the agent choices (including any [paused] marker so the user knows they're forcing through).
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.
- 6d ago First seen · 117 lines · 39 tokens per session scan A ae64e10d2532
run-once is a skill published in the GitHub repository runbear-io/aweek (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,363 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
Orchestrates Volcengine Cloud Detect (云拨测) false-alarm reduction for failing periodic-task dial points. Use for scheduled task scans, retrying failed nodes, control-testing node health, distinguishing real target outages from broken dial points, and suggesting same-type LastMile/IDC/Private replacement nodes. Runs the…