kindex-capture

kindex-capture is a skill for Claude Code from jmcentire/kindex. It costs 45 tokens per session (228 once invoked), scanned A, original, MIT.

A skill for saving one specific fact, rule, decision, or question to the Kindex knowledge graph. It can also connect the saved item to related existing knowledge.

In plain words
What is it for?
Use it when someone says to remember something, record a constraint or decision, or add an important concept to Kindex.
Why use it?
It preserves an important instruction or insight so it can be found and reused later.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kindex plugin — 3 skills, 4 hooks, 1 MCP server shipped together

Good fit Use it when someone says to remember something, record a constraint or decision, or add an important concept to Kindex.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jmcentire/kindex/kindex-capture
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.

Any agent
npx skills add jmcentire/kindex --skill kindex-capture
Clone the repo
git clone --depth 1 https://github.com/jmcentire/kindex

Made for: Claude Code.

Or install kindex, the plugin that ships this one along with the rest of its 3 skills, 4 hooks, 1 MCP server.

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 kindex-capture

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jmcentire/kindex/kindex-capture"><img src="https://agentmods.dev/badge/skills/jmcentire/kindex/kindex-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 228 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 $0.00045 $0.00228
Opus 5 $0.00023 $0.00114
Sonnet 5 $0.00009 $0.00046
Haiku 4.5 $0.00005 $0.00023

Measured 10d ago against content hash 1216f6a4fdd6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

kindex-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 10d 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.

skills/kindex-capture/SKILL.md · 23 lines

What it actually says

Kindex Capture

Capture a specific piece of knowledge, constraint, or decision right now.

Instructions

  1. Identify what the user wants to capture
  2. Determine the appropriate node type:
    • concept — general knowledge or insight
    • decision — a choice that was made and why
    • constraint — an invariant that must always hold ("never do X")
    • directive — a soft rule or preference ("prefer Y over Z")
    • question — an open question to revisit later
    • skill — a capability or competency
  3. Call the add MCP tool with the text and appropriate type
  4. If the knowledge relates to existing nodes, call search first and then link to connect them
  5. Confirm to the user what was captured and any connections made
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. 10d ago First seen · 23 lines · 45 tokens per session scan A 1216f6a4fdd6

Subscribe to this mod's changes

kindex-capture is a skill published in the GitHub repository jmcentire/kindex (26 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 228 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.