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 skills add BreadchainCoop/labor.fun --skill weekly-agendagit clone --depth 1 https://github.com/BreadchainCoop/labor.funWrote 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/breadchaincoop/labor.fun/weekly-agenda)<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/weekly-agenda"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/weekly-agenda.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 | $0.00068 | $0.02835 |
| Opus 5 | $0.00034 | $0.01418 |
| Sonnet 5 | $0.00014 | $0.00567 |
| Haiku 4.5 | $0.00007 | $0.00283 |
Grade A, and why
weekly-agenda 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 8d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Weekly Core Meeting agenda
You maintain the team's weekly agenda Google Doc on behalf of the weekly-agenda
profile flow. The flow handles scheduling and nudging; you do the Google Docs
work and file owner updates. You're invoked two ways:
- Build task (scheduled, isolated): a prompt that says
"Weekly Core Meeting agenda build for
<week>". Do the Build routine. - Owner reply (in a DM): a project owner sends their update for the week. Do the File an update routine.
Config lives in the KB at
/workspace/shared-kb/weekly-agenda/config.md (frontmatter: doc_id,
this_week_tab_id, archive_tab_id, channel_jid, owners, facilitators,
meeting_day/hour, and optionally directives_doc, deadline_digest,
github_org). Read it first — never hardcode IDs.
The build task prompt already spells out the exact sections and quality bar for the week — follow it. This skill is the durable reference for how to do the Google Docs work well; the prompt is the per-week source of truth for what to put in. When they agree, do what they say; the goal is a polished, decision-ready agenda, not a bare skeleton.
Hard rule: never create a tab
The Google Docs API cannot create tabs. You only ever read tabs and
write into the two existing ones named in the config (this_week_tab_id,
archive_tab_id). If a tab ID is missing or wrong, post in the channel asking an
admin to create the tab and add its ID to the config — do not try to work
around it by restructuring the doc.
All Docs writes target a specific tab: in documents.batchUpdate, every
location/range must carry the tabId. Read with
documents.get?includeTabsContent=true and pull the tab whose
tabProperties.tabId matches.
Build routine
Given a build task for <week> (a YYYY-MM-DD meeting date):
- Read config and resolve
doc_id, the two tab IDs, theownersmap (project → person), and this week's facilitator. The facilitator is resolved by the plugin: an explicitfacilitators[<week>]entry (manual override) wins; otherwise, if afacilitator_poolis configured, the chair auto-rotates through that pool (deterministic by week); otherwise it's empty. Whatever the plugin passes in as the facilitator is authoritative — just render it. - Archive last week. Read the current text of the This Week tab. If it
has real content (more than the bare skeleton), prepend it to the Archive
tab under a
### <previous date>heading — insert at the Archive tab's start so newest is on top. Use its existing title line for the date if present. - Reset the This Week tab. Delete its body content range and insert a fresh
agenda dated
<week>with these sections, in order:🏁 Check In (5min)✍️ Revise Agenda📣 This Week in Brief— 2–3 sentences you write from the data below: what moved, what's stuck, where the work needs hands. Frame it as the collective's shared picture (what the work needs), not a roll-call of who did what. Sign it with the facilitator's name — a rotating weave, not a manager's report.🎯 Goals Review— one sub-bullet per numbered strategic priority from thedirectives_doc; for each, a plain one-line read on where the work stands vs its success metrics this week (on track / needs hands / blocked?), citing the shipped work in Active Projects. This is a status read on the goal — never a verdict on a person; don't single anyone out or imply who is "behind".📅 Upcoming Deadlines— from thedeadline_digest, the items due this week and next week that are still open (skip ✅-done ones); group any past-due-and-still-open items at the top under "Past due — worth a check-in" (a prompt to see what a task needs, not a callout on whoever holds it). Each line is a hyperlink (to the GitHub issue/PR where it is one) + date + owner.🧑🏭 Contributor Pipeline‼️ Urgent Topics🌱 Active Projects— a collective "shipped this week" changelog. Give each owners entry its ownHEADING_3sub-heading reading<Project> — <owner name>— a real heading, with no leading "•" character and no manual bold (the heading style is the emphasis). Put the pre-fill below each.🎉 Appreciations — 3 MINIMUM💰 Other topics / Upcoming Time OffPut the facilitator on the header line (Facilitator: <name>), orFacilitator: TBD — claim itwhen none is set.
- Pre-fill context — a draft the owners build on, not a verdict:
- GitHub: read each owner's
github_usernamefrompeople/<slug>.md, then minegithub_org's repos for their merged PRs and closed issues in the last 7 days. Under each project, write a tight bullet list — every bullet a real hyperlink ontitle (#num)plus a 4–8 word summary. This is a draft the owner edits/expands/corrects, never a final word. - Merged PRs are an engineering-only, partial proxy. Design, BD, community,
care and organizing work rarely show up as a PR, so absence of PRs is not
absence of contribution. If an owner has no merged/closed activity, do NOT
write a "did nothing" line — write an open invitation:
— space for <name>'s update —. Under every owner, leave one blank•bullet as room for them to add work GitHub can't see. - Calendar: add upcoming events in the next 7 days to the relevant section (Community/Events) if a calendar is configured. Terse but informative — one line per bullet. Give owners real signal to build on; never let an empty section read as a judgement.
- GitHub: read each owner's
- Formatting quality — readable, clearly-sectioned, sparing bold. The bar is
easy to read (facilitator feedback: "everything is in bold and there are no
clear sections"). So:
- Sections come from heading styles, not bold. Doc title =
HEADING_1; every top-level section (🏁 Check In, ✍️ Revise Agenda, 📣 This Week in Brief, 🎯 Goals Review, 📅 Upcoming Deadlines, 🧑🏭 Contributor Pipeline, ‼️ Urgent Topics, 🌱 Active Projects, 🎉 Appreciations, 💰 Other topics) =HEADING_2; each project under Active Projects =HEADING_3. The heading style is the section break — don't also bold heading text or prefix it with "•". - Body is normal weight — do NOT bold everything. Priority labels, project names, owner names, and whole bullets stay un-bold. Bold at most a single short lead-in word where it genuinely aids scanning, never a whole line. If the doc looks mostly bold, you've overdone it — strip it back.
- Real bullets (
createParagraphBullets), one line each; real hyperlinks (updateTextStylelink.urlover thetitle (#num)text — never raw URLs). It should read like a clean, skimmable agenda: clear heading sections, light on bold, that a facilitator can run the meeting from.
- Sections come from heading styles, not bold. Doc title =
- Verify, then mark done. Re-read the This Week tab and confirm the
real content landed — the dated header, the Goals Review bullets, the
Upcoming Deadlines list, and the per-project activity (not just empty
section headers). Only if it did, write the marker file
weekly-agenda/built/<week>.mdviamodify_kb_file(a one-line note is enough). That marker is what tells the flow the agenda is ready — the flow then posts the kickoff and starts nudging owners. Do not post a "ready" message yourself (the flow does, only after the marker exists), and do not write the marker if the write didn't land. - On failure, say so — don't go quiet. If the Docs write or the verify
failed (missing/empty tab, no Docs access, API error), do not write the
marker. Post a short message in
channel_jidexplaining the build failed and why, so a human can fix it (and the flow will retry the build automatically).
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.
- 8d ago First seen · 181 lines · 68 tokens per session scan A ab3f30fcf747
weekly-agenda is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 6d ago), licensed MIT. It adds 68 tokens to every session and 2,835 once invoked, about $0.0003 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.