A guide for sending and handling messages between agent sessions through a stable registry. It treats each message as a claim that the receiving agent must verify and also records it durably on disk.

Use it to address another agent, send structured messages, verify incoming claims, and preserve the conversation in a durable location.

It prevents messages from being confused by temporary session names and stops an unverified message from replacing reliable project records.

How bredmond1019/claude-sdk-rs configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/ping-agent/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/ping-agent/github.svg)](https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/ping-agent)

Your own site

<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/ping-agent"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/ping-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/ping-agent"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/ping-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,655 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00134	$0.02655
Opus 5.5	$0.00054	$0.01062
Sonnet 5.5	$0.00027	$0.00531
Haiku 4.5	$0.00013	$0.00265

Measured 11d ago against content hash 88eac45baffa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ping-agent 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 11d 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.

.agents/skills/ping-agent/SKILL.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sending, receiving, and answering a ping

Paths below are relative to the brain root — the directory containing brain.toml, found by walking up from wherever you are. This skill is synced into every repo, so a repo-relative link would be wrong in most of them.

A ping is a claim. The receiver verifies it locally before acting on it, and the sender writes it to disk in addition to sending it. Neither half is optional, and this skill is not a role system: every lane agent does the same job — send, receive, verify, respond — in a different repo. The only distinct role in the fleet is the commander (BT.6.D covers that half of the conversation).

Addressing a peer

Address a peer through the BT.6.A registry, not a ListAgents nickname. ListAgents nicknames are unstable across restart and carry no repo, lane, or roadmap — a lane you addressed five minutes ago may be a different nickname now, or gone. The registry turns that volatile nickname into a stable, addressable identity:

<lock_dir>/lane-agents/agent-*.json

lock_dir resolves the same way everywhere in this fleet: --lock-dir flag, else FLEET_LOCK_DIR env var, else a brain.toml discovered by walking up from cwd, joined with .fleet-locks. Each registry record is a lane-agent.schema.json claim — agent_name (the current ListAgents nickname), repo, lane, roadmap, started_at, heartbeat. Read the registry to find who is driving the lane you need; use ListAgents only afterward, to confirm that nickname is still live before you send. Sending to a nickname you have not just confirmed against the registry is how a message gets addressed to a lane that already closed.

Composing: one envelope per kind

Every message is a strict JSON envelope matching .claude/workflows/message.schema.json field-for-field — not a prose format. This is deliberate: the eventual engine-rs structured-output port must be a mechanical translation of an already-typed shape, not a redesign of a format that was never typed in the first place. This skill does not restate the schema's field table — read .claude/workflows/message.schema.json for the authoritative shape; what follows is one worked example per kind, written to:

Read the full file on GitHub · 194 lines

Changes

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.

11d ago First seen · 194 lines · 134 tokens per session scan A 88eac45baffa

Subscribe to this mod's changes

ping-agent is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 134 tokens to every session and 2,655 once invoked, about $0.0005 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 2026-10-26.

Building agents

ping-agent next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ping-agentbredmond1019/claude-sdk-rs	Skill	23	1mo ago	Apache-2.0	A	134	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

claude-sdk-rs: Skill for Claude Code