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 kb-operationsgit 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/kb-operations)<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/kb-operations"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/kb-operations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/kb-operations"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/kb-operations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00035 | $0.01331 |
| Opus 5.5 | $0.00014 | $0.00532 |
| Sonnet 5.5 | $0.00007 | $0.00266 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
kb-operations 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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kb-operations — Knowledge Base Reference
Reference for how Breadbrich Engels manages the structured KB.
Directory Structure
The canonical KB lives in slack_main/context/. Every container reads it via the /workspace/shared-kb/ mount (read-only) and writes through the modify_kb_file tool (the mount itself is read-only by design — never edit files under /workspace/shared-kb/ directly). The orchestrator applies the write to the canonical location and enforces access control.
| Category | Read path (any container) | Write via modify_kb_file (relative path) |
Default Visibility | Description |
|---|---|---|---|---|
| People | /workspace/shared-kb/people/ |
people/ |
private | One file per person |
| Tasks | /workspace/shared-kb/tasks/ |
tasks/ |
open | Structured task tracking (TASK-NNN) |
| Calendar | /workspace/shared-kb/calendar/ |
calendar/ |
open | Events, schedules, deadlines |
| Artifacts | /workspace/shared-kb/artifacts/ |
artifacts/ |
open | Documents, creative works, equipment |
| Financials | /workspace/shared-kb/financials/ |
financials/ |
restricted | Budget, expenses, invoices |
| Dashboards | /workspace/shared-kb/dashboards/ |
dashboards/ |
restricted | Visual reports, HTML dashboards |
Writing the KB (any container, including DMs)
KB writes are not restricted to the main group. Any container — including
telegram_<user> / slack_<user> DMs and other non-main groups — can create
or update KB files by calling the modify_kb_file tool with a path relative
to the KB context dir (e.g. tasks/TASK-001.md). The orchestrator gates the
write on the sender, not the channel:
- Allowlisted sender (anyone who resolves to a KB people file + identity
mapping) → full read/write from any group, including DMs. This is the default
cooperative model — see
docs/COOPERATIVE-MODE.mdandrules/access-control/README.md. Do not decline a KB write just because the request came from a DM; if the requester is allowlisted, write it. - Unknown sender (no identity mapping) → reads of open-visibility content only; KB writes are rejected by the orchestrator.
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.
- 1mo ago First seen · 121 lines · 35 tokens per session scan A d53c23f6d424
kb-operations is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,331 once invoked, about $0.0001 per session on Opus 5.5. 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
gog
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
box
Box manages cloud files, sharing, search, and metadata.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
recipe-save-email-attachments
Find Gmail messages with attachments and save them to a Google Drive folder.
material-organizer
Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.