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 spuentesp/lain --skill lain-coordinationgit clone --depth 1 https://github.com/spuentesp/lainWrote 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/spuentesp/lain/lain-coordination)<a href="https://agentmods.dev/skills/spuentesp/lain/lain-coordination"><img src="https://agentmods.dev/badge/skills/spuentesp/lain/lain-coordination/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/spuentesp/lain/lain-coordination"><img src="https://agentmods.dev/badge/skills/spuentesp/lain/lain-coordination.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 | $0.00057 | $0.00632 |
| Opus 5.5 | $0.00023 | $0.00253 |
| Sonnet 5.5 | $0.00011 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
lain-coordination 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 19d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lain coordination — work beside other agents
Multiplayer plumbing is hidden from the default surface because
hooks usually drive it — hooks/<agent>/ scripts call
claim_files / heartbeat / release_files directly. Tools are
callable by name even when hidden, but load_package makes them
appear in tools/list; many MCP clients only permit tools their
cached list contains. Load these packages only when you are
managing the coordination yourself.
Load them
load_package("session") for claiming, load_package("social")
for the roster, load_package("notes") for handoffs — or set
LAIN_TOOL_PROFILE=session,social,notes at config time for a
coordinator agent. Reconnect the client if the tools do not appear.
Claim discipline (session)
register_agentonce (name yourself meaningfully).- Before editing:
detect_overlapon the files/symbols you will touch — if a peer holds them, coordinate first. claim_fileswith an intent and a TTL you can honour; refresh withheartbeat;release_filesthe moment you are done.my_claims/list_occupancy/get_world_stateanswer "who holds what" at any moment.
Awareness (social)
list_active_agents (who is here), who_am_i (what the server
thinks you are), list_subagents, get_audit_log (recent
coordination events in this workspace), unregister_agent on exit.
Handoffs (notes)
leave_handoff_note when your work continues elsewhere — say what
you changed and what you did NOT do. get_pending_handoffs when you
start. lain_intent / list_active_intents for the plan board;
add_annotation / list_annotations / resolve_annotation for
notes pinned to code.
Example payloads (copy verbatim, fill in values):
add_annotation → target={"kind":"symbol","symbol":"MyFn","repo_id":"..."},
kind="note", body="..."
leave_handoff_note → body="[scope:auth] did X; Y still open", scope="auth"
Rules of thumb
- Claims are advisory coordination, not locks — still re-check before you write.
- Keep TTLs short and heartbeats honest; an expired claim drops (by design) and a stale one is worse than none.
- Never claim files "just in case" — claim when you are about to edit.
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.
- 19d ago First seen · 62 lines · 57 tokens per session scan A c30f6f5eeb63
lain-coordination is a skill published in the GitHub repository spuentesp/lain (9 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 632 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
revise-roadmap
Revise an implementation roadmap based on critic feedback.
validate-roadmap-scope
Roadmap scope validation gate - evaluates roadmap coverage and sizing before phase planning.
supervisor
Agentico supervisor — operate the Agentic Orchestrator server on the user's behalf through the agentico api helper.
review-implementation-design
Implementation review Design axis - live-runs visible UI quality and originality.
review-implementation-functionality-evidence
Implementation review Functionality/Evidence axis - audits plan satisfaction and verification evidence.
validate-plan-performance
Plan performance validation gate - evaluates performance and scalability before implementation.