kc-cache-insight

kc-cache-insight is a skill for Claude Code from iamcxa/kc-claude-plugins. It costs 40 tokens per session (2,690 once invoked), scanned A, original, MIT.

A tool for saving a written understanding of a source file or module in a shared context store. The note covers what the file does, how it is used, its main code elements, and its limitations.

In plain words
What is it for?
Use it to record an insight about a file, inspect the context store, search saved insights, or view its status and metrics.
Why use it?
It preserves useful understanding after code exploration so it can be found later instead of being reconstructed from scratch. It also provides status, search, and usage information for saved notes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the kc-hyperfocus plugin — 4 skills, 1 agent, 1 MCP server shipped together

Good fit Use it to record an insight about a file, inspect the context store, search saved insights, or view its status and metrics.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iamcxa/kc-claude-plugins/kc-cache-insight
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 iamcxa/kc-claude-plugins --skill kc-cache-insight
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code.

Or install kc-hyperfocus, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 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 kc-cache-insight

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-cache-insight.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-cache-insight)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/kc-cache-insight"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/kc-cache-insight.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,690 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 $0.00040 $0.02690
Opus 5 $0.00020 $0.01345
Sonnet 5 $0.00008 $0.00538
Haiku 4.5 $0.00004 $0.00269

Measured 8d ago against content hash c1d669294c41, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kc-cache-insight 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 8d 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.

kc-hyperfocus/skills/kc-cache-insight/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kc-cache-insight [file_path | --dashboard | --search | --status | --metrics]

Cache an insight about a file to the context lake, or view cache status.

Routes

No args or <file_path>

  1. If <file_path> provided → generate insight for that file
  2. If no args → generate insight for the most recently discussed file in conversation
  3. If no file can be determined (no args AND no file discussed in conversation) → fall back to --status route. Do NOT guess a file path or error out silently.
  4. Read the target file to validate it exists and refresh your understanding. If Read fails (file not found), report: "File {path} not found — cannot generate insight." and stop. Do NOT fabricate an insight for a nonexistent file.
  5. Produce a 3-8 sentence summary in English answering:
    • What does this file do?
    • How is it used? (callers, consumers)
    • What are the key functions/classes?
    • What are the gotchas / dependencies / limitations? Language rule: Always write insights in English, regardless of the conversation language. This ensures consistency for FTS5 search and cross-session readability.
  6. Present the insight to the user for confirmation
  7. On confirmation → call store_insight with source: "manual"
  8. Report: "Cached insight for {file_path} to context lake"

--search [query | file_path]

Search cached insights. Two modes:

  • --search src/foo.ts → exact file path lookup
  • --search "impact analysis" → FTS5 keyword search across all cached insights

Call search_insights with file_path (if looks like a path) or query (if looks like keywords). Present each result with: file path, source, freshness (fresh/stale), and the full insight content.

If no results found, report: "No cached insights found for '{query}'. Try a broader search term, or cache an insight first with /kc-cache-insight <file_path>."

--dashboard

Overview of ALL repos' context lake status. Run this Bash command and present the output as a table:

Read the full file on GitHub · 199 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. 8d ago First seen · 199 lines · 40 tokens per session scan A c1d669294c41

Subscribe to this mod's changes

kc-cache-insight is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 2,690 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 2026-08-31.

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