instinct-import

instinct-import is a command for coding agents from Fmarzochi/EGC. It costs 5 tokens per session (404 once invoked), scanned A, original, Apache-2.0.

A command for importing learned coding habits, called instincts, from a file, URL, or teammate share. It checks the JSON format, skips duplicates, adjusts confidence, and adds valid entries to local storage.

In plain words
What is it for?
Use it to bring coding patterns and recommendations from another source into the continuous-learning system.
Why use it?
It avoids manually copying reusable lessons into the learning system and helps prevent duplicate or malformed entries.

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/fmarzochi/egc/instinct-import
Clone the repo
git clone --depth 1 https://github.com/Fmarzochi/EGC

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-import

README.md
[![agentmods](https://agentmods.dev/badge/commands/fmarzochi/egc/instinct-import.svg)](https://agentmods.dev/commands/fmarzochi/egc/instinct-import)
Your own site
<a href="https://agentmods.dev/commands/fmarzochi/egc/instinct-import"><img src="https://agentmods.dev/badge/commands/fmarzochi/egc/instinct-import.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00005 $0.00404
Opus 5 $0.00003 $0.00202
Sonnet 5 $0.00001 $0.00081
Haiku 4.5 $0.00001 $0.00040

Measured today against content hash d62e317b9848, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

instinct-import 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 today.

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.

.opencode/commands/instinct-import.md · 89 lines

What it actually says

Instinct Import Command

Import instincts from a file or URL: $ARGUMENTS

Your Task

Import instincts into the continuous-learning-v2 system.

Import Sources

File Import

/instinct-import path/to/instincts.json

URL Import

/instinct-import https://example.com/instincts.json

Team Share Import

/instinct-import @teammate/instincts

Import Format

Expected JSON structure:

{
  "instincts": [
    {
      "trigger": "[situation description]",
      "action": "[recommended action]",
      "confidence": 0.7,
      "category": "coding",
      "source": "imported"
    }
  ],
  "metadata": {
    "version": "1.0",
    "exported": "2025-01-15T10:00:00Z",
    "author": "username"
  }
}

Import Process

  1. Validate format - Check JSON structure
  2. Deduplicate - Skip existing instincts
  3. Adjust confidence - Reduce confidence for imports (×0.8)
  4. Merge - Add to local instinct store
  5. Report - Show import summary

Import Report

Import Summary
==============
Source: [path or URL]
Total in file: X
Imported: Y
Skipped (duplicates): Z
Errors: W

Imported Instincts:
- [trigger] (confidence: 0.XX)
- [trigger] (confidence: 0.XX)
...

Conflict Resolution

When importing duplicates:

  • Keep higher confidence version
  • Merge application counts
  • Update timestamp

TIP: Review imported instincts with /instinct-status after import.

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. today First seen · 89 lines · 5 tokens per session scan A d62e317b9848

Subscribe to this mod's changes

instinct-import is a command published in the GitHub repository Fmarzochi/EGC (48 stars, last pushed today), licensed Apache-2.0. It adds 5 tokens to every session and 404 once invoked, about $0.0000 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 2026-09-03.