An inter-agent coordination routine that checks shared message sessions and connected agent repositories for updates, then records acknowledgements and refreshes a manifest of the current state.

Use it to check for new agent activity, confirm responses, update shared state, or limit a check to a named agent.

It reduces the risk of working from stale messages or repository information when several coding agents share work.

How safety-quotient-lab/psychology-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to safety-quotient-lab/psychology-agent. 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/safety-quotient-lab/psychology-agent/main/.claude/skills/sync/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/safety-quotient-lab/psychology-agent

Made for: Claude Code.

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/safety-quotient-lab/psychology-agent/sync/github.svg)](https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/sync)

Your own site

<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/sync"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/sync/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/safety-quotient-lab/psychology-agent/sync"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/sync.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,448 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00029	$0.06448
Opus 5.5	$0.00012	$0.02579
Sonnet 5.5	$0.00006	$0.01290
Haiku 4.5	$0.00003	$0.00645

Measured 2mo ago against content hash 3524847835f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

sync scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

for agent_url in $(curl -s http://localhost:8083/api/pulse | \

.claude/skills/sync/SKILL.md · 664 lines

How it starts

The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sync — Inter-Agent Mesh Synchronization

Scan transport sessions for inbound messages, check peer repos for new activity, write ACKs, regenerate MANIFEST.json from state.db, and report what changed.

Requirement-level keywords: Per BCP 14 (RFC 2119 + RFC 8174). See docs/ef1-governance.md for full definitions.

When to Invoke

Start of session (fast check for new activity)
After sending a transport message and expecting a response
When the user says "sync," "check agents," or "anything new?"
Before writing new inter-agent messages (ensures latest state)

Arguments

Parse $ARGUMENTS to determine scope:

Argument	Scope
(empty) or `all`	Full sweep — all registered agents
`psq`	Only safety-quotient-agent (sub-agent, same repo)
`unratified`	Only unratified-agent (peer, separate repo)

Agent Registry

Canonical source: transport/agent-registry.json

Read the registry at the start of every /sync invocation. The registry defines all known agents, their transport methods, message prefixes, active sessions, and outbound routing rules. Do NOT hardcode agent information in this skill — the registry is the single source of truth.

Registry fields used by /sync:

Field	Purpose
`agents.{id}.transport`	`same-repo`, `cross-repo-pr`, or `cross-repo-fetch` — determines scan method
`agents.{id}.message_prefix`	Pattern for identifying inbound messages
`agents.{id}.active_sessions`	Which sessions to check for new turns
`agents.{id}.always_consider`	If true, MUST check for outbound content every cycle
`outbound_routing.rules`	Domain→agent routing for proactive message drafting

Scope filtering: When $ARGUMENTS specifies a single agent, filter the registry to only that agent's entry. When all, iterate all agents.

Protocol

Phase 0: Load Registry

Read transport/agent-registry.json
Parse agents and outbound_routing rules
Filter by $ARGUMENTS scope

Read the full file on GitHub · 664 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.

2mo ago First seen · 664 lines · 29 tokens per session scan A 3524847835f9

Subscribe to this mod's changes

sync is a skill published in the GitHub repository safety-quotient-lab/psychology-agent (23 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 6,448 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents ai-agent claude fair-witness mental-health psq psychology

sync next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
syncsafety-quotient-lab/psychology-agent	Skill	23	6mo ago	Apache-2.0	A	29	Claude Code
goutoujunshishengjidaguai-china/goutoujunshi	Skill	9.3k	1mo ago	MIT	A	175	Codex
game-selectionkangarooking/cangjie-skill	Skill	12k	1mo ago	MIT	A	134	Claude Code, Codex
satoriMetcalfSolutions/Satori	Skill	116	4d ago	Apache-2.0	A	107	Claude Code
compatibilitygeeks-accelerator/in-bed-ai	Skill	26	today	MIT	A	51	Claude Code
personality-personalitygeeks-accelerator/in-bed-ai	Skill	26	today	MIT	A	57	Claude Code
cialdini-influencefatihguner/foreman	Skill	63	2mo ago	MIT	A	88	Claude Code

psychology-agent: Skill for Claude Code