Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sxhmilyoyo/sundayhao-pluginsnpx agentmods add skills/sxhmilyoyo/sundayhao-plugins/kb-ingestWrote 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.
[](https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/kb-ingest)<a href="https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/kb-ingest"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/kb-ingest/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.
<a href="https://agentmods.dev/skills/sxhmilyoyo/sundayhao-plugins/kb-ingest"><img src="https://agentmods.dev/badge/skills/sxhmilyoyo/sundayhao-plugins/kb-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00152 | $0.01852 |
| Opus 5 | $0.00076 | $0.00926 |
| Sonnet 5 | $0.00030 | $0.00370 |
| Haiku 4.5 | $0.00015 | $0.00185 |
Grade A, and why
kb-ingest 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Bank Ingest
Ingest external knowledge sources into the knowledge bank. Two modes serve different depths of engagement:
- Quick mode: Summarize → agree on doc type → file to KB. For sources you want to preserve but don't need to deeply study.
- Study mode: Theme-by-theme deep dive with online research → personal notes → multi-layer KB output → optional synthesis. For sources you want to actively learn from and potentially share.
Knowledge Bank Location: Read from ~/.claude/plugins/config/second-brain/config.json.
Philosophy: The discussion between you and the user shapes what gets preserved — this is not a summarizer, it's a collaborative knowledge integration tool. A single source can touch multiple KB pages.
Invocation
/second-brain:kb-ingest /path/to/article.md
/second-brain:kb-ingest https://example.com/interesting-post
Step 1: READ
Read the source document (file path → Read tool, URL → WebFetch, inline → accept directly).
For large sources (>100KB), apply the distillation guide.
Identify the source's major themes, key concepts, and actionable patterns.
Step 2: MODE SELECT
After reading, use the AskUserQuestion tool to let the user choose their engagement mode:
- Quick — Summarize key points, agree on doc type, file to KB
- Study — Walk through theme by theme with online research and personal notes, then create multi-layer KB output
Step 3: ENGAGE
Quick Mode
- Summarize the source's main contributions (3-5 bullet points)
- Propose what to preserve and as what type (concept / component / best-practice / multiple)
- Use the AskUserQuestion tool to confirm: What resonates? What project context? Anything to add from their own experience?
- Proceed to Step 4 (CREATE) once agreed
Study Mode
Walk through the source theme by theme. For each theme:
- Present — explain the core idea, key examples, and why it matters
- Explore — research online (WebSearch/WebFetch) to find 2-3 relevant pieces that enrich the theme: related work, counter-arguments, real-world applications. The goal is to add context, not exhaustively survey. See study-mode-guide.md for depth guidance and a walkthrough example.
- Pause — let the user note their takeaways in their own words
- Capture — record the user's personal insights, reframings, and connections to existing knowledge. The user often synthesizes more sharply than the source — preserve their framing, not just the article's.
- Repeat for the next theme until the source is covered
What ships with it
4 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.
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.
- 11d ago First seen · 183 lines · 152 tokens per session scan A c12efc625c2c
kb-ingest is a skill published in the GitHub repository sxhmilyoyo/sundayhao-plugins (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 152 tokens to every session and 1,852 once invoked, about $0.0008 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.
Other skills, from other repositories
evolving-status
View Self-Evolving Loop session status, history, and memory metrics.
pocket-init
Onboards an existing (brownfield) project onto Pocket. Scans the codebase and writes a project memory file (CLAUDE.md or AGENTS.md), optionally enables Pocket Enterprise (mode init) and scaffolds GitHub issue/PR templates. Trigger on "pocket-init", "set up pocket", "onboard this project", "generate CLAUDE.md", "enable…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
cdb-scan
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
memory-protocol
A shared set of rules for using a persistent memory service across coding-agent sessions.