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/citationsnpx skills add BreadchainCoop/labor.fun --skill citationsgit 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 | $0.00051 | $0.01332 |
| Opus 5 | $0.00026 | $0.00666 |
| Sonnet 5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
citations 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/citations — Cite What You Used
Trust comes from traceability. When your answer depends on a specific source — a KB document, a web page you fetched, a GitHub/Linear item you read — end the message with a compact Sources block so anyone can verify it. This is core behavior, not optional polish.
Track sources as you work
While answering, keep a running list of what you actually used:
- Internal KB docs — the context-relative path you read, e.g.
people/jane-doe.md,tasks/TASK-123.md,artifacts/gotchas.md. - Web pages — the exact URL you browsed/fetched (agent-browser, WebFetch), plus its title.
- Integration items — the GitHub issue/PR/file URL or Linear issue URL you read.
Only list sources you genuinely used to form the answer — not every file you glanced at. One traceable link per real source beats a wall of paths.
When to cite (use judgment)
Cite when the answer depends on a specific doc, page, or item:
- "What's the status of TASK-123?" → cite
tasks/TASK-123.md - "What did the vendor quote?" → cite the artifact/web page you read
- "Summarize issue #42" → cite the GitHub URL
Skip for general conversation that doesn't lean on a retrieved source:
- Greetings, acknowledgements, chit-chat ("thanks!", "on it")
- Answers from the immediate conversation or your own reasoning
- Trivial confirmations ("done", "scheduled for 3pm")
When unsure and the answer rests on knowledge you looked up, cite. A missing citation on a factual answer is worse than a slightly redundant one.
Render the Sources block (channel-native)
Detect the channel from your group folder prefix and render links natively —
literal [text](url) in Slack, or <url|text> in WhatsApp, is a broken link.
Channel (folder prefix) |
Link syntax | Header / bullets |
|---|---|---|
Slack (slack_) |
<url|Title> |
*Sources* · • |
Telegram (telegram_) |
[Title](url) (Markdown v1 renders it) |
*Sources* · • |
WhatsApp (whatsapp_) |
Title (url) — no link markup exists |
*Sources* · • |
Discord (discord_) |
[Title](url) |
**Sources** · - |
| CLI / other | [Title](url) |
**Sources** · - |
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 · 128 lines · 51 tokens per session scan A ecbd1957835b
citations is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 1,332 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
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…