knowledgine: Skill for Claude Code

.agents/skills/knowledgine-capture/SKILL.md

knowledgine-capture is a skill for Claude Code, Codex from 3062-in-zamud/knowledgine. It costs 70 tokens per session (837 once invoked), scanned A, original, MIT.

A skill for saving useful technical knowledge in a local knowledge base after solving a problem or making an important decision. The saved notes can be reused in later sessions and by team members.

In plain words
What is it for?
Use it after fixing a non-trivial bug, choosing an architecture, finding a reusable pattern, applying outside documentation, or completing a meaningful refactoring.
Why use it?
It prevents valuable explanations, bug fixes, design choices, and reusable patterns from being lost when a work session ends.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is 3062-in-zamud/knowledgine's own configuration. It tells Claude Code and Codex how to work on knowledgine 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 knowledgine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 3062-in-zamud/knowledgine. 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/3062-in-zamud/knowledgine/develop/.agents/skills/knowledgine-capture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/3062-in-zamud/knowledgine

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 knowledgine-capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/3062-in-zamud/knowledgine/knowledgine-capture/github.svg)](https://agentmods.dev/skills/3062-in-zamud/knowledgine/knowledgine-capture)
Your own site
<a href="https://agentmods.dev/skills/3062-in-zamud/knowledgine/knowledgine-capture"><img src="https://agentmods.dev/badge/skills/3062-in-zamud/knowledgine/knowledgine-capture/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 knowledgine-capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/3062-in-zamud/knowledgine/knowledgine-capture"><img src="https://agentmods.dev/badge/skills/3062-in-zamud/knowledgine/knowledgine-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 837 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 $0.00070 $0.00837
Opus 5 $0.00035 $0.00418
Sonnet 5 $0.00014 $0.00167
Haiku 4.5 $0.00007 $0.00084

Measured 12d ago against content hash 37eccd9065c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

knowledgine-capture 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.

.agents/skills/knowledgine-capture/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

knowledgine-capture

Purpose

Persist valuable learnings from the current session into the local knowledge base so they are available for future sessions and team members. The knowledge base is only as useful as what is recorded into it.

When to Use

Capture knowledge when any of the following events occur in the session:

  1. Bug fix — You identified a root cause and applied a solution
  2. Design decision — You chose one approach over alternatives with reasoning
  3. Pattern discovery — You found a reusable pattern worth applying elsewhere
  4. Troubleshooting — You worked through a non-obvious diagnosis process
  5. External knowledge — You applied insights from documentation, articles, or Stack Overflow
  6. Refactoring — You improved existing code with a clear before/after

When NOT to Use

  • Trivial edits (typo fixes, formatting changes) that contain no transferable insight
  • Highly project-specific one-off changes with no reuse value
  • Duplicate entries: first search with search_knowledge to check if the knowledge already exists

How to Capture (MCP Tool)

Use the capture_knowledge MCP tool:

capture_knowledge(
  content: string,   // Full explanation: problem + solution + context
  title: string,     // Short descriptive title (max ~80 chars)
  tags: string[],    // 2–5 tags from the standard taxonomy
  source?: string    // Optional: URL, filename, or reference source
)

How to Capture (CLI Alternative)

knowledgine capture add "<content>" --title "<title>" --tags "<tag1>,<tag2>"

Content Format

Structure each capture as three parts:

  1. Problem / Context — What situation triggered this learning?
  2. Solution / Decision — What was done and how?
  3. Rationale / Notes — Why this approach? What alternatives were considered?

Example:

**Problem**: TypeScript threw "Type 'unknown' is not assignable to type 'User'" when
parsing API response.

**Solution**: Added a type guard function isUser(val: unknown): val is User that checks
for required fields before narrowing the type.

**Rationale**: Using 'as User' cast was unsafe because the API response structure could
change. The type guard provides runtime validation and compile-time safety.

Read the full file on GitHub · 98 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 98 lines · 70 tokens per session scan A 37eccd9065c0

Subscribe to this mod's changes

knowledgine-capture is a skill published in the GitHub repository 3062-in-zamud/knowledgine (3 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 837 once invoked, about $0.0003 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens