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 franmelx/que-paso-ayer --skill coordinate-project-relaygit clone --depth 1 https://github.com/franmelx/que-paso-ayerWrote 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/franmelx/que-paso-ayer/coordinate-project-relay)<a href="https://agentmods.dev/skills/franmelx/que-paso-ayer/coordinate-project-relay"><img src="https://agentmods.dev/badge/skills/franmelx/que-paso-ayer/coordinate-project-relay/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/franmelx/que-paso-ayer/coordinate-project-relay"><img src="https://agentmods.dev/badge/skills/franmelx/que-paso-ayer/coordinate-project-relay.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 | $0.00082 | $0.00728 |
| Opus 5.5 | $0.00033 | $0.00291 |
| Sonnet 5.5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
coordinate-project-relay 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinate project relay
Use the MCP as a shared operational memory, not as a generic note store.
Start safely
- Detect the repository root and project marker without modifying files.
- Resolve the known project id and call
project_association_checkbefore any project knowledge tool. - Stop without reading or writing shared context when the result is not
associatedandactive. - Ask the user before registering, activating, splitting, merging, or archiving a project. Call
project_registeronly after explicit approval and setapprovedByUser: trueonly when that approval actually occurred. - Call
participant_registerfor the effective human and agent after explicit approval. Record model, specialties and capabilities usingunknownrather than guessing. Reuse an identical registered profile instead of creating aliases. - Start collaboration with
session_startfor each actor before meaningful editing, and keep sessions alive withsession_heartbeat.
Synchronize work
- Call
knowledge_querywithafterRevisionwhen a project cursor is available; otherwise query the relevant terms, services, components and constraints. - Surface newer revisions and overlapping scopes before changing related components. Use
active_sessionsand heartbeat signals to reason about in-flight work from other actors. - Identify relevant projects, services, connections, rules and modification considerations.
- Re-synchronize before modifying a shared contract or a scope claimed by another session.
Preserve causality
For each meaningful modification, capture:
- observed problem or requested outcome;
- cause and certainty:
observed,hypothesis,confirmed,refuted, orunknown; - rules, limits and invariants that must remain true;
- services or cross-project connections imposing constraints;
- affected paths, components, interfaces and environments;
- risks if the behavior changes again;
- evidence and checks actually performed;
- pending work and review conditions.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 59 lines · 82 tokens per session scan A 66db63084a1e
coordinate-project-relay is a skill published in the GitHub repository franmelx/que-paso-ayer (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 728 once invoked, about $0.0003 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
wenlan-handoff
End a work session. Stores durable captures, writes a narrative session log, and automatically applies typed item-level deltas to the current Space Brief. Invoked as /wenlan-handoff.
wenlan-brief
Read the current Space-owned project Brief from Wenlan. With an optional topic, appends separately labeled related context from the same Space. Invoked as /wenlan-brief [topic] when resuming work or asking to catch up.
sibyl
Persistent memory and task coordination for this project. Invoke for any prompt about past work, project state, in-progress tasks, prior decisions, gotchas, or capturing a non-obvious learning. Also covers semantic search across project knowledge and external docs.
capture-task
Capture a new task — create a draft or pending Task record from a rough idea or detailed spec. Use when asked to "add a task", "log a bug", "create a task", or "add to backlog".
refine-backlog
Refine the backlog — screen drafts, remove duplicates, fill in missing details, classify, link, and move to pending.
implement-task
Pick up and work on a binder Task — investigate bugs, discuss open questions, design solutions, write tests, or implement code. Use when asked to "work on", "pick up", "implement", or "fix" a task.