seed-extraction

seed-extraction is a skill for Claude Code, Codex from DojoGenesis/mcp. It costs 73 tokens per session (2,993 once invoked), scanned A, original, MIT.

A skill for turning lessons from past work into reusable written patterns, called seeds. It also explains how to recognize, write, and apply those patterns.

In plain words
What is it for?
It is for documenting repeated lessons, mistakes, insights, and practices that others may reuse.
Why use it?
It helps preserve useful lessons instead of leaving them as vague notes or losing them after a project ends.

Skill for Claude CodeCodex

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 skills/dojogenesis/mcp/seed-extraction
Any agent
npx skills add DojoGenesis/mcp --skill seed-extraction
Clone the repo
git clone --depth 1 https://github.com/DojoGenesis/mcp

Made for: Claude Code, Codex.

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 seed-extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/dojogenesis/mcp/seed-extraction.svg)](https://agentmods.dev/skills/dojogenesis/mcp/seed-extraction)
Your own site
<a href="https://agentmods.dev/skills/dojogenesis/mcp/seed-extraction"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/seed-extraction.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,993 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00073 $0.02993
Opus 5 $0.00036 $0.01496
Sonnet 5 $0.00015 $0.00599
Haiku 4.5 $0.00007 $0.00299

Measured 4d ago against content hash 149302aa182b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seed-extraction 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 4d 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.

internal/skills/bundled/wisdom-garden/seed-extraction/SKILL.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seed Extraction

Version: 1.1 Author: Tres Pies Design Purpose: Extract, document, and apply reusable patterns (seeds) from experiences.


I. Philosophy: Every Experience Contains Seeds

A seed is a reusable pattern that emerged from experience -- not theory, not abstraction, but something that actually happened and taught something transferable. The practice of seed extraction is learning to see these patterns, name them precisely, and plant them where they'll grow.

Seeds compound. A seed planted today becomes a reference point next week, a skill component next month, and part of your institutional DNA next quarter. The compounding cycle -- experience > seed > skill > ecosystem -- is the engine of institutional learning.

But not every observation is a seed. The test is reusability: can someone else, facing a similar situation, apply this pattern and get value? If yes, it's a seed. If it's too specific to one context, it's a note. If it's too vague to act on, it's a platitude.

II. When to Use This Skill

  • After completing a project or milestone that produced learnings
  • When you notice a pattern repeating across multiple situations
  • During memory compression (Tier A > Tier B promotion)
  • When a mistake teaches something reusable -- failures are often the richest soil
  • When a technique or approach works surprisingly well and could apply elsewhere
  • When a reframe changes how you think about a class of problems

When NOT to use: If the knowledge is a simple fact ("use port 3000 for dev") it's documentation, not a seed. If it's a multi-step process, it's a skill candidate, not a seed. Seeds encode principles, not procedures.

III. The Seed Extraction Workflow

Step 1: Identify the Candidate

Look for raw material in recent experiences. The richest sources are:

Source What to Look For
Decisions that worked well What principle guided the decision?
Decisions that failed What was the wrong assumption?
Patterns across multiple instances What keeps repeating?
Insights that changed thinking What do you see differently now?
Tensions or tradeoffs navigated What framework helped you choose?

Read the full file on GitHub · 319 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. 4d ago First seen · 319 lines · 73 tokens per session scan A 149302aa182b

Subscribe to this mod's changes

seed-extraction is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,993 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

drt-analyze

Analyze DRT cluster health for a given time range. Reconstructs the operations timeline, checks CockroachDB metrics (availability, latency, storage, changefeeds, jobs, goroutines, admission control, LSM, KV prober) and logs for anomalies, correlates findings with disruptive operations to distinguish expected…

cockroachdb/cockroach · 149 tokens

redux-to-swr

Migrate React components from Redux + Saga to SWR hooks. Use when converting data fetching from Redux store (reducers, sagas, selectors, connect HOC) to SWR-based hooks in CockroachDB DB Console or cluster-ui.

cockroachdb/cockroach · 53 tokens

prune-npm-overrides

Audit the pnpm overrides a repo already carries, remove the ones upstream has since fixed, and require a justification comment on every one that stays. The counterpart to fix-npm-vulnerability. Use when asked to check, clean up, or prune the overrides, or when an override's tracking issue comes up for review.

thunder-id/thunderid · 71 tokens

mma-investigator

Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.

cockroachdb/cockroach · 47 tokens

engflow-artifacts

Use when downloading test logs, artifacts, or outputs.zip from EngFlow build invocations. Use when investigating CockroachDB CI test failures hosted on mesolite.cluster.engflow.com.

cockroachdb/cockroach · 41 tokens