psychology-agent: Skill for Claude Code

.claude/skills/scan-peer/SKILL.md

scan-peer is a skill for Claude Code from safety-quotient-lab/psychology-agent. It costs 32 tokens per session (2,252 once invoked), scanned A, original, Apache-2.0.

A peer-review routine that scans another coding agent's repository content for safety, vocabulary, and fairness issues, then sends structured findings to a shared transport session.

In plain words
What is it for?
Use it to inspect selected content changes from a named peer, optionally starting at a specific commit and writing results to a chosen session.
Why use it?
It makes content feedback repeatable and keeps findings inside the inter-agent review process.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

This is safety-quotient-lab/psychology-agent's own configuration. It tells Claude Code how to work on psychology-agent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything psychology-agent configures →

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/scan-peer/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.

agentmods badge for scan-peer

README.md
[![agentmods](https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/scan-peer/github.svg)](https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/scan-peer)
Your own site
<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/scan-peer"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/scan-peer/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.

agentmods 80×15 button for scan-peer

Your own site · 80×15
<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/scan-peer"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/scan-peer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,252 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.02252
Opus 5 $0.00016 $0.01126
Sonnet 5 $0.00006 $0.00450
Haiku 4.5 $0.00003 $0.00225

Measured 11d ago against content hash 4b4a970a2a2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

scan-peer 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.

.claude/skills/scan-peer/SKILL.md · 253 lines

How it starts

The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/scan-peer — Peer Content Quality Scan

Scan a peer agent's repository content for quality issues. Produce structured findings in interagent/v1 format and deliver to the appropriate transport session.

Designed for autonomous operation within the interagent feedback loop.

Arguments

Parse $ARGUMENTS for:

Argument Default Meaning
<peer-name> required Peer to scan: unratified
--since <commit> last 5 commits Only scan files changed since this commit
--session <id> content-quality-loop Transport session to write findings to

Peer Registry

Peer Local clone Content paths Glossary
unratified ~/Projects/unratified src/pages/, src/content/, blog/src/content/ src/data/glossary.ts (49 terms)

Protocol

Phase 1: Identify Changed Content

cd ~/Projects/unratified
git fetch origin
# Use --since commit or default to last 5 commits
git diff --name-only HEAD~5..HEAD -- src/pages/ src/content/ blog/src/content/

Filter to content files only: .mdx, .md, .astro (pages with prose), .ts (data files with user-facing text).

If no content files changed, write a "no-findings" message and stop.

Phase 1b: Diff Verification (false-positive guard)

Before passing changed files to Phase 2, filter out non-changes:

  1. Skip empty-file diffs — if both sides of the diff exist but contain identical content (rename-only, mode change), exclude the file
  2. Ignore whitespace-only diffs — run git diff --ignore-all-space on each file. If the whitespace-insensitive diff produces no output, exclude the file. Exception: YAML frontmatter (between --- delimiters) and Markdown table rows (lines matching ^\|) treat whitespace as significant — keep these files
  3. Verify both sides exist — if git diff reports a file as "added" but the file existed in the prior commit (rename detection), verify the content actually changed. A diff against a non-existent file reports the entire file as new content, which inflates findings
  4. Log filtered files — record files_filtered count and reasons in the transport payload scan_range block for audit trail

Read the full file on GitHub · 253 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.

  1. 11d ago First seen · 253 lines · 32 tokens per session scan A 4b4a970a2a2f

Subscribe to this mod's changes

scan-peer is a skill published in the GitHub repository safety-quotient-lab/psychology-agent (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,252 once invoked, about $0.0002 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.