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/lookatitude/guild/wiki-querynpx skills add lookatitude/guild --skill wiki-querygit clone --depth 1 https://github.com/lookatitude/guildWrote 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/lookatitude/guild/wiki-query)<a href="https://agentmods.dev/skills/lookatitude/guild/wiki-query"><img src="https://agentmods.dev/badge/skills/lookatitude/guild/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 | $0.00000 | $0.02415 |
| Opus 5 | $0.00000 | $0.01208 |
| Sonnet 5 | $0.00000 | $0.00483 |
| Haiku 4.5 | $0.00000 | $0.00242 |
Grade A, and why
guild-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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guild:wiki-query
Implements the knowledge layer query contract: wiki structure + filterable frontmatter, load-by-role categorization, scale-transition (rg/filesystem under ~200 pages, guild-memory MCP above), and the read side of the memory write path that all specialists depend on.
Read-only counterpart to guild:wiki-ingest. Every page that skill writes carries a source_refs: [<slug>] back-citation into .guild/raw/sources/<slug>/; this skill honors it so "where does this come from" always returns the original URL or file path, not just the LLM summary.
Input
- query (required) — free-text, matched against page body and frontmatter. An empty query is allowed only when at least one filter is set.
- filters (optional, combinable):
category—context | standard | product | entity | concept | decision | source(thetype:enum). Mapped internally to the plural directory (standard→standards/). Reject plural forms with an error pointing at the singular enum.owner— specialist slug; matchesowner:.confidence—low | medium | high; matches exactly.updated_since— ISO-8601 date; returns pages withupdated_at:on or after it.tag— matched against atags:array if present, else against body headings.
- source_resolve (optional, default
true) — dereference each result'ssource_refs:to.guild/raw/sources/<slug>/metadata.jsonand include the original URL/path.
If the caller passes an unknown category, reject the query with the list of valid categories — never silently fall back to a full-wiki walk.
Search strategy
Two paths, chosen by scale; pick one per invocation (no mid-query switching):
- Under ~200 pages — ripgrep + filesystem (default). Search root =
.guild/wiki/<category>/ifcategoryset, else.guild/wiki/(excludingindex.md,log.md,lint-*.md). Full-text match viaGrep(case-insensitive by default),Globto enumerate when only filters are set. Extract the frontmatter block and filter onowner/confidence/updated_since/tag— never regex-parse YAML. Rank exact-phrase > bag-of-words > frontmatter-only, tie-breakupdated_atdesc thenconfidencehigh→low. Cap 20 (raise vialimit). - Above ~200 pages — guild-memory MCP (optional, P6). First check
mcp.stdio_available(resolved config) — see## MCP-availability gate: when false, the MCP stdio transport is declared unavailable, so do not attempt the MCP call; route tofsScaninstead. When true, delegate to its BM25search; post-filterconfidence/updated_sinceif unsupported; on an unreachable MCP despitestdio_available: true, fall back tofsScan(or ripgrep) and note the degradation.
What ships with it
2 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.
- 4d ago First seen · 98 lines · 0 tokens per session scan A ce77259643a1
guild-wiki-query is a skill published in the GitHub repository lookatitude/guild (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,415 tokens. 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
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…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
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…