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 khalilbenaz/claude-skills-collection --skill message-protocolgit clone --depth 1 https://github.com/khalilbenaz/claude-skills-collectionWrote 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/khalilbenaz/claude-skills-collection/message-protocol)<a href="https://agentmods.dev/skills/khalilbenaz/claude-skills-collection/message-protocol"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/message-protocol/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/khalilbenaz/claude-skills-collection/message-protocol"><img src="https://agentmods.dev/badge/skills/khalilbenaz/claude-skills-collection/message-protocol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.03209 |
| Opus 5 | $0.00045 | $0.01605 |
| Sonnet 5 | $0.00018 | $0.00642 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
message-protocol 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 10d 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Message Protocol
Quand utiliser ce skill
Utilise ce skill dès que deux agents ou plus doivent s'échanger des tâches, des résultats ou des signaux de contrôle de façon fiable et traçable — qu'il s'agisse d'une architecture mono-processus (event bus local) ou distribuée (Redis Streams, RabbitMQ, Kafka).
Workflow en 10 étapes
1. Définir le format de message standard
Tout message doit contenir ces champs minimaux :
| Champ | Type | Description |
|---|---|---|
message_id |
UUID v4 | Identifiant unique du message |
sender |
string | ID de l'agent émetteur |
recipient |
string | ID de l'agent cible ou "broadcast" |
type |
enum | task_request / task_result / status_update / error / heartbeat / control |
payload |
dict | Données utiles sérialisées |
timestamp |
ISO 8601 UTC | Heure d'émission |
correlation_id |
UUID v4 | Relie requête et réponse |
schema_version |
string | Ex. "1.2" — pour la compatibilité |
import uuid
from datetime import datetime, timezone
from dataclasses import dataclass, field
from typing import Any
@dataclass
class AgentMessage:
message_id: str = field(default_factory=lambda: str(uuid.uuid4()))
sender: str = ""
recipient: str = ""
type: str = "" # task_request | task_result | status_update | error | heartbeat | control
payload: dict[str, Any] = field(default_factory=dict)
timestamp: str = field(default_factory=lambda: datetime.now(timezone.utc).isoformat())
correlation_id: str | None = None
schema_version: str = "1.0"
2. Typer les messages — un type = un schéma
Chaque type possède un schéma de payload documenté et validé via Pydantic :
from pydantic import BaseModel, Field
class TaskRequestPayload(BaseModel):
task_id: str
task_type: str
input_data: dict
priority: int = Field(default=5, ge=0, le=9)
deadline_seconds: int | None = None
class TaskResultPayload(BaseModel):
task_id: str
status: str # "success" | "partial" | "failed"
output_data: dict
duration_ms: int
class ErrorPayload(BaseModel):
error_code: str # "TIMEOUT" | "VALIDATION_FAILED" | "AGENT_UNAVAILABLE"
error_message: str
retry_hint: bool
retry_after_seconds: int | None = None
fallback_suggestion: str | None = None
stack_trace: str | None = None # debug only, masquer en prod
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.
- 10d ago First seen · 316 lines · 90 tokens per session scan A 1166f642c272
message-protocol is a skill published in the GitHub repository khalilbenaz/claude-skills-collection (22 stars, last pushed 16d ago), licensed MIT. It adds 90 tokens to every session and 3,209 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
api-patterns
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe retries. Triggers: API design, REST, GraphQL, OpenAPI, Swagger, error response, HTTP status, rate limit.
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
java-patterns
Java: Spring Boot, CompletableFuture, records, sealed types, JPA/Hibernate, virtual threads. Triggers: Java, Spring, JPA, Hibernate, Maven, Gradle, virtual thread, sealed class.
explain
Explains code/architecture with Mermaid diagrams and sequence flows. Triggers: what does X do, how does Y work, explain code, sequence diagram.
common-sense-index-investing-bogle
Apply John Bogle index investing rules for low-cost funds, asset allocation, fees, taxes, ETFs, advisers, and buy-hold discipline.
medplum-rules
Medplum (FHIR healthcare) coding rules: style, patterns, security, testing. Triggers: medplum.config.mts, medplum.config.ts, FHIR, Medplum, Bot, Subscription, Questionnaire.