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.
npx agentmods add skills/hogu-dev/llmkb/kb-ingestnpx skills add hogu-dev/llmkb --skill kb-ingestgit clone --depth 1 https://github.com/hogu-dev/llmkbWrote 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/hogu-dev/llmkb/kb-ingest)<a href="https://agentmods.dev/skills/hogu-dev/llmkb/kb-ingest"><img src="https://agentmods.dev/badge/skills/hogu-dev/llmkb/kb-ingest.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00479 |
| Opus 5 | $0.00028 | $0.00239 |
| Sonnet 5 | $0.00011 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
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 3d 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.
What it actually says
kb-ingest
Ingest a source document into an llmkb knowledge base: turn it into a summary
page and fold its ideas into the concept and entity pages, keeping the index,
log, and links consistent.
When to use
A user has dropped a file in the KB's raw/ directory (or points you at one)
and wants it filed into the wiki.
Steps
- Read the discipline. Open
SCHEMA.mdat the KB root and follow its conventions for this project. - Read the source in
raw/. Identify the key claims, entities, and concepts. - Write the summary page under
wiki/summaries/. Use the required frontmatter (type: summary;sourceslists theraw/path). Keep it a faithful condensation, self-contained, with[[wikilinks]]to the concepts and entities it touches. - Update concept pages under
wiki/concepts/: create a page for each new cross-cutting idea, or extend an existing one. Agent-authored synthesis is a concept page with an empty (or session-ref)sources. - Update entity pages under
wiki/entities/for people, orgs, systems, or products the source introduces or expands. - Update the catalog. Run
llmkb reindexto rebuildwiki/index.mdfrom frontmatter, then append one line towiki/log.md:## [YYYY-MM-DD] ingest | <source title>. - Lint and fix. Run
llmkb lintand resolve every error it reports (broken links, orphans, missing-from-index) before finishing.
Done when
llmkb lint reports no errors and the source is represented by a summary page
plus any concept/entity updates, all linked and indexed.
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.
- 3d ago First seen · 42 lines · 55 tokens per session scan A 4121db24ff09
kb-ingest is a skill published in the GitHub repository hogu-dev/llmkb (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 479 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.
Other skills, from other repositories
brainstorm
Guided game concept ideation — from zero idea to a structured game concept document. Uses professional studio ideation techniques, player psychology frameworks, and structured creative exploration.
kb-fediverse-json-ld
Background knowledge about how JSON-LD works on the Fediverse and in ActivityPub, including the difference between @id and id, @type and type (keyword aliasing via @context), the many forms a value can take (string, object with @value, object with @id, array, language-tagged value), the four JSON-LD document forms…
consistency-check
Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.
create-architecture
Guided, section-by-section authoring of the master architecture document for the game. Reads all GDDs, the systems index, existing ADRs, and the engine reference library to produce a complete architecture blueprint before any code is written. Engine-version-aware: flags knowledge gaps and validates decisions against…
design-review
Reviews a game design document for completeness, internal consistency, implementability, and adherence to project design standards. Run this before handing a design document to programmers.
onboard
Generates a contextual onboarding document for a new contributor or agent joining the project. Summarizes project state, architecture, conventions, and current priorities relevant to the specified role or area.