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/querynpx skills add runbear-io/aweek --skill querygit 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 | $0.00029 | $0.02072 |
| Opus 5 | $0.00015 | $0.01036 |
| Sonnet 5 | $0.00006 | $0.00414 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
query 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aweek:query
Slug-returning filter over the aweek agent roster. Use this skill any time a
request names a subset of agents rather than a single one — e.g. "the active
marketers", "every paused researcher", "agents whose persona mentions X.com".
Reads identity (name, description, system prompt) live from
.claude/agents/<slug>.md, and lifecycle state from the existing stores; never
mutates anything.
Downstream skills (/aweek:plan, /aweek:manage, future /aweek:bulk-plan)
are expected to consume the agents[].id list from this skill's JSON result
instead of hand-rolling grep over .claude/agents/*.md.
Filters
All filters are optional. Omitting every one returns the full roster.
| Filter | Semantics |
|---|---|
role |
Case-insensitive substring match against the subagent .md description. "marketer" → matches "Content marketer", "Senior Brand Marketer", etc. |
keyword |
Case-insensitive substring search across name + description + system-prompt body. Use this when the distinguishing trait isn't in the one-line description — e.g. keyword: "x.com" to find every persona that publishes to X.com. Result carries matchedOn so the skill can show where it hit. |
status |
One (or comma-separated many) of active, paused, idle, running, missing-subagent. Matches the lifecycle states used by /aweek:summary, plus the synthetic missing-subagent for orphaned aweek JSON. |
budget |
no-limit (weekly limit is 0), under (utilization < 100%), or over (utilization ≥ 100%). |
Notes on interaction
roleandkeywordrequire a readable.mdfile. Rows whose.mdis missing drop out of those filters automatically; usestatus=missing-subagent(without role/keyword) to find orphans.status=activemeans "has an approved plan with pending/in-progress work". Paused agents never matchstatus=active.- Filters combine with AND. "Active marketers" =
role=marketer status=active.
Instructions
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 · 218 lines · 29 tokens per session scan A 2ac89e7c76e2
query is a skill published in the GitHub repository runbear-io/aweek (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 2,072 once invoked, about $0.0001 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.