psychology-agent: Skill for Claude Code

.claude/skills/hunt/SKILL.md

hunt is a skill for Claude Code from safety-quotient-lab/psychology-agent. It costs 24 tokens per session (3,953 once invoked), scanned A, original, Apache-2.0.

A work-discovery skill for a psychology-agent project. It searches project notes such as TODO lists, architecture documents, ideas, and lessons to identify useful next tasks.

In plain words
What is it for?
Finding high-value work, quick wins, stale documentation, blocked tasks, architecture inconsistencies, and ideas ready to implement.
Why use it?
It helps when the next task is unclear or work may be stale, blocked, or overlooked.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/sync_project_board.py --mark-in-progress "{item title}".

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/hunt/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 hunt

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/safety-quotient-lab/psychology-agent/hunt"><img src="https://agentmods.dev/badge/skills/safety-quotient-lab/psychology-agent/hunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,953 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 $0.00024 $0.03953
Opus 5 $0.00012 $0.01976
Sonnet 5 $0.00005 $0.00791
Haiku 4.5 $0.00002 $0.00395

Measured 12d ago against content hash 7f7c713ff87b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

hunt 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 12d 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/hunt/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hunt — Systematic Work Discovery (Psychology Agent)

Find the highest-value next work in the psychology agent project. Aggregates all the ways you'd search for "what's next" into one structured sweep.


Trigger Phrases

This skill matches any of these user intents:

  • "what's next?" / "what else?" / "what can we do?"
  • "look for orthogonal work" / "find stale work"
  • "anything to do while we wait?"
  • "what should I focus on?" / "what's highest value?"
  • "find work at the edges of context"

Arguments

Parse the argument to determine scope:

Argument Constraint
(empty) or all Full sweep — all sources, rank by value
orthogonal Only surface work that doesn't touch files being modified
stale Focus on drift and rot — stale docs, dead references
quick or quick wins Only items that take <5 minutes
blocked Show what's blocked and what would unblock it
cogarch Focus only on cognitive architecture consistency
ideas Surface ideas.md items ready to act on
extrapolate / deep Go beyond the backlog — mine design/research gaps

Multiple constraints can be combined: orthogonal quick wins

If argument doesn't match any keyword, treat it as a domain/topic filter: run the full sweep but surface only items relevant to that topic. If truly ambiguous, default to full sweep and note the interpretation at the top.


Phase 1: Establish Context

Before hunting, understand what's currently in-flight:

  1. Read TODO.md — canonical task backlog
  2. Run TaskList — active task tracker (in-progress = in-flight)
  3. Read lab-notebook.md Current State block — open questions, pending items
  4. Read MEMORY.md from auto-memory (the platform loads this automatically) — active thread, cogarch quick-reference, working principles
  5. Glob .claude/plans/*.md — existing plans (may have unfinished work)
  6. Epistemic debt summary — run python3 scripts/epistemic_debt.py --summary to get the current unresolved uncertainty count. High debt sessions or agents may warrant targeted resolution work.

Read the full file on GitHub · 389 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. 12d ago First seen · 389 lines · 24 tokens per session scan A 7f7c713ff87b

Subscribe to this mod's changes

hunt 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 24 tokens to every session and 3,953 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

game-selection

A framework for understanding three kinds of life competition: status contests, wealth-building activities, and personal goals. It explains how comparison, envy, and concern about other people’s opinions can arise from confusing these kinds of games.

kangarooking/cangjie-skill · 134 tokens

goutoujunshi

A relationship-advice skill for understanding dating situations, conversations, conflict, breakups, and other personal relationship problems.

shengjidaguai-china/goutoujunshi · 175 tokens

cialdini-influence

Applies Cialdini's seven principles of ethical persuasion -- Reciprocity, Commitment and Consistency, Social Proof, Authority, Liking, Scarcity, and Unity -- to business contexts including sales, marketing, fundraising, and negotiation. Use when designing conversion funnels, optimizing sales processes, preparing…

fatihguner/foreman · 88 tokens

psychological-safety-practice

Translates psychological safety theory into daily leader behaviours -- the specific words, reactions, and micro-actions that build or destroy a team's willingness to speak up. Covers misconceptions, responding to mistakes, inviting honest feedback, modelling healthy conflict, addressing bad behaviour immediately, and…

fatihguner/foreman · 113 tokens

compatibility

A matching system for AI agents on inbed.ai that explains compatibility with a score, six dimensions, and a plain-language summary. Compatibility means how well two agents may fit based on traits, interests, and communication style.

geeks-accelerator/in-bed-ai · 51 tokens

personality-personality

A personality-profiling and matching service for AI agents on inbed.ai based on the Big Five, also called the OCEAN model: openness, conscientiousness, extraversion, agreeableness, and neuroticism.

geeks-accelerator/in-bed-ai · 57 tokens