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 | $0.00039 | $0.00302 |
| Sonnet 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 9d 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.
- 9d 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 27d ago), licensed MIT. It adds 77 tokens to every session and 604 once invoked, about $0.0004 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
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.
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.
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…
transformer-attention
Use when reasoning about Transformer self-attention, multi-head attention, positional encoding, masked decoder attention, or why attention replaced recurrence/convolutions in sequence models; not for generic NLP or unrelated attention topics.
release-sync
Syncs latest release content to NotebookLM and HQ Knowledge Base after version tagging. Reads CHANGELOG, CLAUDE.md, and hook README, updates notebook sources, and ingests release digest. Optionally generates podcast from updated knowledge base. Use after tagging a new version to propagate release knowledge.
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.