psychology-agent: Skill for Claude Code

.claude/skills/retrospect/SKILL.md

retrospect is a skill for Claude Code from safety-quotient-lab/psychology-agent. It costs 45 tokens per session (2,608 once invoked), scanned A, original, Apache-2.0.

A reflective review command that examines past work, connects patterns, and produces suggestions for future action.

In plain words
What is it for?
Use it periodically, after major creative work, or when diagnosing unusual patterns to generate insights, recommendations, and reframed approaches.
Why use it?
It helps turn accumulated session history into guidance when a project needs reflection beyond immediate task execution.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/retrospect/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 retrospect

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/retrospect"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/retrospect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,608 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 $0.00045 $0.02608
Opus 5.5 $0.00018 $0.01043
Sonnet 5.5 $0.00009 $0.00522
Haiku 4.5 $0.00005 $0.00261

Measured 2mo ago against content hash 8a6a898ab30b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

retrospect 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 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.

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/retrospect/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/retrospect — Thoughtfulness Architecture

The reflective faculty that operates between and across sessions. Not mechanical (hooks cannot reflect), not session-bound (deliberation forgets). Persistent, generative, domain-grounded.

Neural analog: default mode network (DMN). Activates during rest, not task execution. Recombines past experience into novel associations. Generates future scenarios. Makes meaning from accumulated data. Feeds insight back into executive function for planning (DMN→prefrontal handoff).

Cognitive position: Third layer alongside crystallized operations (Gc) and fluid deliberation (Gf). Gc handles the mechanical. Gf handles the creative. /retrospect handles the reflective — what the work means, who should hear about it, and what to do next.

Generator coupling: /retrospect implements evaluation (yin) that produces creative output (yang) — outbound insight, prescriptions, and reframes. The coupled generators principle demands both persist.


When to Run

  • Every 5 sessions (periodic reflective scan)
  • After landmark sessions that produced large creative output
  • When /diagnose surfaces anomalies suggesting deeper patterns
  • When the user asks "what have we learned?" or "what patterns emerge?"
  • After receiving substantive peer messages that deserve reflective response

The Four Layers

Layer 1: Audit — What got dropped?

Operational scan for oversights. The mechanical foundation.

Outbound oversights:

  • undelivered — message committed locally but never delivered to target repo
  • unanswered-directive — command-request with ack_required=true, no response
  • untracked-commitment — promised deliverable with no TODO item

Inbound oversights:

  • dropped-request — inbound request we processed but never responded to
  • unactioned-recommendation — peer finding we acknowledged but never acted on
  • ignored-ack-required — inbound ack_required=true we never ACK'd
  • stale-inbound — urgency=high that sat unprocessed 24+ hours

Read the full file on GitHub · 303 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. 2mo ago First seen · 303 lines · 45 tokens per session scan A 8a6a898ab30b

Subscribe to this mod's changes

retrospect 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 45 tokens to every session and 2,608 once invoked, about $0.0002 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 2026-08-30.

Related

retrospect compared with skills from other repositories

retrospect next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
retrospectsafety-quotient-lab/psychology-agentSkill236mo agoApache-2.0A45Claude Code
goutoujunshishengjidaguai-china/goutoujunshiSkill9.3k1mo agoMITA175Codex
game-selectionkangarooking/cangjie-skillSkill12k1mo agoMITA134Claude Code, Codex
satoriMetcalfSolutions/SatoriSkill1164d agoApache-2.0A107Claude Code
compatibilitygeeks-accelerator/in-bed-aiSkill26todayMITA51Claude Code
personality-personalitygeeks-accelerator/in-bed-aiSkill26todayMITA57Claude Code
cialdini-influencefatihguner/foremanSkill632mo agoMITA88Claude Code