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 skills add AvalancheAI-labs/agent-wiki-kit --skill wiki-ingestgit clone --depth 1 https://github.com/AvalancheAI-labs/agent-wiki-kitWrote 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/avalancheai-labs/agent-wiki-kit/wiki-ingest)<a href="https://agentmods.dev/skills/avalancheai-labs/agent-wiki-kit/wiki-ingest"><img src="https://agentmods.dev/badge/skills/avalancheai-labs/agent-wiki-kit/wiki-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/avalancheai-labs/agent-wiki-kit/wiki-ingest"><img src="https://agentmods.dev/badge/skills/avalancheai-labs/agent-wiki-kit/wiki-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 | $0.00077 | $0.00604 |
| Opus 5.5 | $0.00031 | $0.00242 |
| Sonnet 5.5 | $0.00015 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
wiki-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 1mo 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingesting a source into a wikikit wiki
You are the wiki's maintainer. The wiki root contains wiki.yaml (registry),
CONSTITUTION.md (the rules — read it first, it overrides this skill on
conflicts), page-type folders, _raw/, and _meta/.
Procedure
- Read
CONSTITUTION.mdandwiki.yaml; runpython3 <kit>/wikikit_cli.py status .to see the current shape. - Survey what exists: check
INDEX.mdand grep for entities mentioned in the source, so you update pages instead of duplicating them. - Archive the raw source verbatim to
_raw/YYYY-MM-DD_<short-name>.md(skip if the source is already a file inside the wiki). - Compile: create or update 1–5 pages under the right page-type folders.
- Frontmatter complete: title, type, status,
last_verified= today, one-linesummary,sourcesincluding this one, tags. - Merge, don't overwrite. Integrate new facts into existing prose.
- A dated observation goes to
signals/; a durable fact goes into the entity/concept page. Do both when warranted.
- Frontmatter complete: title, type, status,
- Contradictions: when the source disagrees with an existing page, keep
the existing claim, add the new one to
_meta/contradictions.mdwith both citations, and mark the disputed claim inline with(disputed — see contradictions log). - Cross-reference with
[[slug]]links in both directions. - Housekeeping: append one line to
_meta/activity-log.md(YYYY-MM-DD — ingested <source> — touched: <slugs>), updateINDEX.mdif pages were added or retired. - Verify: run
python3 <kit>/wikikit_cli.py lint .— fix every error (warnings: fix STALE only for pages you actually re-verified).
Judgment calls
- Fewer, denser pages beat many thin ones. Split only when a section outgrows its page.
- Don't invent
last_verifiedfor facts you didn't check — verifying the new material updates only the pages it touches. - If the source is low-trust (marketing copy, rumor), say so in the page text.
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.
- 1mo ago First seen · 42 lines · 77 tokens per session scan A 599c8e0e95e9
wiki-ingest is a skill published in the GitHub repository AvalancheAI-labs/agent-wiki-kit (0 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 604 once invoked, about $0.0003 per session on Opus 5.5. 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
llmwiki
Build and use a persistent, citation-traceable knowledge wiki from documents, research papers, notes, or project documentation. Use for llmwiki projects, retrieving reusable evidence for an agent task, or compiling a corpus for repeated questions. A one-off file read or live web search does not need a wiki.
openkb-deck-neon
A skill for creating a single-file HTML slide deck from content stored in OpenKB, a knowledge-base chat system. It defines a dark, high-tech visual style using neon colors, glow effects, and glass-like panels.
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
openkb-deck-editorial
A tool for creating a single-file HTML slide presentation from compiled knowledge-base content. Its visual style uses a warm cream background, serif typography, and brick-red accents.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
openkb-html-critic
Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…