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/helicerat/llm-wiki-loop/wiki-querynpx skills add helicerat/llm-wiki-loop --skill wiki-querygit clone --depth 1 https://github.com/helicerat/llm-wiki-loopWrote 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/helicerat/llm-wiki-loop/wiki-query)<a href="https://agentmods.dev/skills/helicerat/llm-wiki-loop/wiki-query"><img src="https://agentmods.dev/badge/skills/helicerat/llm-wiki-loop/wiki-query.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 5.1 | $0.00055 | $0.00485 |
| Opus 5 | $0.00028 | $0.00243 |
| Sonnet 5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
wiki-query 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 5d 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
wiki-query
Read in this order, stop early
Cost discipline is the feature. A vault that has to be read in full to be queried is a folder of files with extra steps.
wiki/index.md— the catalogue. Often enough on its own- Frontmatter grep —
^(claim|status|n|tags|summary):across the vault. Rank by exact title match, then tag match, then summary match - Windowed grep —
grep -A 10 -B 2on the candidates. Fifteen to thirty lines each. Most factual questions die here without a single page being opened - Full read — at most 3 pages, at most one hop of links from them
If step 4 does not answer it, the answer is not in the wiki. Say that instead of assembling something plausible from fragments.
Answer
Cite pages with wikilinks. An uncited sentence in an answer is the model talking, and it should be marked as such.
When the answer rests on a claim, state its state and its n. Not as a footnote — in
the sentence:
Bullets tracked with higher reach on artifact-anchored posts,
rule, n=4. Opening length showed no effect,candidate, n=1 — one run, treat it as nothing.
A user cannot calibrate on an answer that hides how thin the evidence is. This is the single most important line in this skill.
If a relevant claim is retired, say so and give the reason. That is what retired claims
are kept for.
File it back
A good answer is a page. Comparisons, syntheses, and connections discovered while answering are worth as much as ingested sources and disappear into chat history by default.
Ask before filing. Then write it, link it, and log:
## [YYYY-MM-DD] query | question -> page created
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.
- 5d ago First seen · 50 lines · 55 tokens per session scan A 9ca98756c058
wiki-query is a skill published in the GitHub repository helicerat/llm-wiki-loop (6 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 485 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
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.
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.…
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…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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.
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…