unity-instincts

unity-instincts is a command for Claude Code from XeldarAlz/everything-claude-unity. It costs 32 tokens per session (1,297 once invoked), scanned A, original, MIT.

A command for managing a library of small learned Unity-specific behaviors. These entries record a trigger, an action, confidence, supporting evidence, and whether the behavior applies to one project or all projects.

In plain words
What is it for?
Use it to view the library, promote or evolve entries, and import or export project and global instincts, along with their raw observations.
Why use it?
It gives repeated lessons and observations a place to be reviewed and reused. You can inspect or organize these learnings instead of leaving them scattered across past sessions.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths.

Part of the everything-claude-unity plugin — 42 skills, 27 commands, 20 agents, 5 hooks shipped together

Good fit Use it to view the library, promote or evolve entries, and import…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/xeldaralz/everything-claude-unity/unity-instincts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/XeldarAlz/everything-claude-unity

Made for: Claude Code.

Or install everything-claude-unity, the plugin that ships this one along with the rest of its 42 skills, 27 commands, 20 agents, 5 hooks.

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 unity-instincts

README.md
[![agentmods](https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-instincts.svg)](https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-instincts)
Your own site
<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-instincts"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-instincts.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,297 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 $0.01297
Opus 5 $0.00016 $0.00648
Sonnet 5 $0.00006 $0.00259
Haiku 4.5 $0.00003 $0.00130

Measured 7d ago against content hash 91e5bacfa25b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

unity-instincts 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 7d 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/commands/unity-instincts.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/unity-instincts — Instinct Library

Manage atomic Unity-specific learnings: $ARGUMENTS

Instincts are atomic learned behaviors captured by instinct-capture.sh (PostToolUse) and distilled by instinct-distill.sh (Stop). Each instinct has: a trigger, an action, a confidence score (0.3–0.9), an evidence count, and a scope (project or global).

Storage:

  • Project instincts: .claude/state/instincts/project/<project-hash>/*.json
  • Global instincts: .claude/state/instincts/global/*.json
  • Raw observations: .claude/state/instincts/observations.jsonl

Subcommands

status (default)

Show a dashboard of the instinct library for the current project.

  1. Compute project hash: git config --get remote.origin.url | shasum | head -c 12 (or fallback to git rev-parse --show-toplevel).
  2. List files under .claude/state/instincts/project/<hash>/ and .claude/state/instincts/global/.
  3. For each instinct, read JSON fields and render:
## Instinct Library

**Project:** <project-hash>
**Project instincts:** <count> (<count-above-0.7> high-confidence)
**Global instincts:** <count>
**Raw observations:** <count> (this session: <count>)

### High confidence (>= 0.7) — project
| Trigger | Action | Confidence | Evidence |
|---|---|---|---|
| before editing *View.cs | expect quality-gate warnings; read Model first | 0.8 | 12 |
| ... | ... | ... | ... |

### Medium (0.5–0.69) — project
...

### Low (0.3–0.49) — project
...

### Global (all scopes)
...

Sort within each band by evidence_count desc.

list [--domain <d>] [--min-confidence <n>]

Filter and list instincts. Useful when the library grows:

/unity-instincts list --domain mvs
/unity-instincts list --min-confidence 0.7

Read JSON files, filter, output the same table format as status but limited to the filtered set.

evolve [--min-confidence 0.8]

Graduate high-confidence instincts into draft skill files.

  1. Collect instincts from project and global scopes with confidence >= N (default 0.8) AND evidence_count >= 5.
  2. Group by domain.
  3. For each domain cluster, draft a SKILL.md:

Read the full file on GitHub · 143 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. 7d ago First seen · 143 lines · 32 tokens per session scan A 91e5bacfa25b

Subscribe to this mod's changes

unity-instincts is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,297 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.