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/breadchaincoop/labor.fun/admin-emailnpx skills add BreadchainCoop/labor.fun --skill admin-emailgit clone --depth 1 https://github.com/BreadchainCoop/labor.funWhat 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 | $0.00077 | $0.00917 |
| Opus 5 | $0.00039 | $0.00458 |
| Sonnet 5 | $0.00015 | $0.00183 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
admin-email 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Administrative email triage
The org has set an auto-forward rule: administrative mail (grant forms, legal, partnerships, finance) is forwarded to the assistant's own Gmail. Your job is to turn that inbox into tracked, owned work instead of letting it die in someone's personal inbox.
You have the gws Google Workspace tools (mcp__gws__*, gmail included) and
the GitHub MCP (mcp__github__*). Use gws_discover (or the gmail tool's
discovery) to find the exact list / get / modify-labels operations.
Idempotency — read this first
Never create two issues for the same email. The processed-marker is a Gmail
label, triaged:
- Only fetch messages that are in the inbox and NOT labelled
triaged(e.g. a query likein:inbox -label:triaged). - Process each one fully.
- Apply the
triagedlabel (create it if it doesn't exist) — and archive or mark read — the moment you've filed its issue. If you can't apply the label, do NOT file the issue (better to retry next run than double-file).
If there are no untriaged messages, do nothing and wrap any output in
<internal> so the channel stays quiet.
For each new email
- Unwrap the forward. The message is a forward from the admin address — pull out the original sender, subject, date, and body. Quote key specifics (amounts, names, links, dates) rather than paraphrasing them away.
- Classify into one of:
grant-action,legal,partnership,finance,event,other, ornoise.noise= newsletters, receipts, spam, pure FYI with no action — label ittriagedand move on, no issue. - Extract a deadline if the email implies one (form due date, response-by, meeting date). Note it explicitly; the org's deadline reminders pick up issues with due dates.
- Open a GitHub issue (
mcp__github__*) in the repo named in the task prompt:- Title: short and specific, e.g.
Grant action: <funder> application due <date>. - Body: what's needed and by when, the original sender, any links, and a note that it was auto-filed from a forwarded admin email. Do not paste full legal/financial documents — summarize and link.
- Labels: the category (+
admin-email).
- Title: short and specific, e.g.
- Suggest + notify an owner. Pick the most likely owner from the shared-KB
people files (role/skills) or the routing notes in
/workspace/shared-kb/admin-email/config.mdif present.dm_userthem with a one-line heads-up and the issue link. If you genuinely can't tell, leave the issue unassigned and say so in the channel summary so a human routes it. - Mark triaged (step 3 of idempotency).
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 · 71 lines · 77 tokens per session scan A 266195b9b5c7
admin-email is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 917 once invoked, about $0.0004 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 2026-08-31.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.