instinct-export

instinct-export is a command for coding agents from raja21068/AutoResearch. It costs 4 tokens per session (421 once invoked), scanned A, a copy of instinct-export, MIT.

A command that exports learned coding patterns, called instincts, into a shareable JSON file. It supports filtering by confidence or category and can write to a chosen path.

In plain words
What is it for?
Use it to export all instincts, only high-confidence ones, or instincts from a selected category, then inspect an export summary.
Why use it?
It makes useful project knowledge portable so it can be shared, reviewed, or reused elsewhere.

Command

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.

agentmods
npx agentmods add commands/raja21068/autoresearch/instinct-export
Clone the repo
git clone --depth 1 https://github.com/raja21068/AutoResearch

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 instinct-export

README.md
[![agentmods](https://agentmods.dev/badge/commands/raja21068/autoresearch/instinct-export.svg)](https://agentmods.dev/commands/raja21068/autoresearch/instinct-export)
Your own site
<a href="https://agentmods.dev/commands/raja21068/autoresearch/instinct-export"><img src="https://agentmods.dev/badge/commands/raja21068/autoresearch/instinct-export.svg" alt="Measured on agentmods" height="20"></a>
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 421 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% copy Near-identical to another mod 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 $0.00004 $0.00421
Opus 5 $0.00002 $0.00211
Sonnet 5 $0.00001 $0.00084
Haiku 4.5 $0.00000 $0.00042

Measured yesterday against content hash ea63bf9e6e63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instinct-export 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 yesterday.

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.

Origin

This is a copy

97% identical to instinct-export — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/commands/instinct-export.md · 94 lines

What it actually says

Instinct Export Command

Export instincts for sharing with others: $ARGUMENTS

Your Task

Export instincts from the continuous-learning-v2 system.

Export Options

Export All

/instinct-export

Export High Confidence Only

/instinct-export --min-confidence 0.8

Export by Category

/instinct-export --category coding

Export to Specific Path

/instinct-export --output ./my-instincts.json

Export Format

{
  "instincts": [
    {
      "id": "instinct-123",
      "trigger": "[situation description]",
      "action": "[recommended action]",
      "confidence": 0.85,
      "category": "coding",
      "applications": 10,
      "successes": 9,
      "source": "session-observation"
    }
  ],
  "metadata": {
    "version": "1.0",
    "exported": "2025-01-15T10:00:00Z",
    "author": "username",
    "total": 25,
    "filter": "confidence >= 0.8"
  }
}

Export Report

Export Summary
==============
Output: ./instincts-export.json
Total instincts: X
Filtered: Y
Exported: Z

Categories:
- coding: N
- testing: N
- security: N
- git: N

Top Instincts (by confidence):
1. [trigger] (0.XX)
2. [trigger] (0.XX)
3. [trigger] (0.XX)

Sharing

After export:

  • Share JSON file directly
  • Upload to team repository
  • Publish to instinct registry

TIP: Export high-confidence instincts (>0.8) for better quality shares.

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. yesterday First seen · 94 lines · 4 tokens per session scan A ea63bf9e6e63

Subscribe to this mod's changes

instinct-export is a command published in the GitHub repository raja21068/AutoResearch (2 stars, last pushed 3mo ago), licensed MIT. It adds 4 tokens to every session and 421 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to instinct-export, differing in 2 lines, and is treated as a copy.