Wiki QuerySAFE
A framework-agnostic, git-native standard for defining AI agents
Overview
A framework-agnostic, git-native standard for defining AI agents
799d6d0ad18cOBSERVED · 2026-10-07What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: wiki-query description: "Query the wiki to answer questions. Searches wiki pages, synthesizes answers with citations, and optionally files valuable answers back as new wiki pages. Use when the user asks a question about the knowledge base." allowed-tools: Read Write Edit Glob Grep --- # Wiki Query Answer questions by searching and synthesizing from the wiki. ## Workflow ### Step 1: Search the wiki 1. Read `memory/wiki/index.md` to find relevant pages 2. Use Grep to search for specific terms across `memory/wiki/` 3. Read the most relevant pages (usually 3-10) ### Step 2: Synthesize an answer - Combine information from multiple wiki pages - Cite sources: reference both wiki pages and the underlying raw documents - Note confidence level — distinguish well-sourced claims from inferences - Flag if the wiki has gaps on this topic ### Step 3: Present the answer Format depends on the question: - **Factual question** — direct answer with citations - **Comparison** — markdown table comparing entities/concepts - **Overview** — structured summary with sections - **Analysis** — synthesis with explicit reasoning chain ### Step 4: File back (if valuable) If the answer represents a useful synthesis that doesn't exist as a wiki page: 1. Ask the user: "This answer synthesizes information that isn't captured in the wiki yet. Should I file it as a new page?" 2. If yes: create a new wiki page in `memory/wiki/` 3. Update `memory/wiki/index.md` 4. Append to `memory/log.md`: ``` ## [YYYY-MM-DD] query-filed | Page Title - Question: [original question] - Pages referenced: [list] - New page: memory/wiki/page-name.md ``` ## Key Insight Good answers should not disappear into chat history. A comparison you asked for, an analysis, a connection you discovered — these are valuable wiki content. Filing them back means your explorations compound in the knowledge base just like ingested sources do.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
799d6d0ad18cfull audit observations/trust-audit/skill/open-gitagent__wiki-query.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 799d6d0ad18c | SAFE | B | 89 | first audit |
Questions
What does the Wiki Query skill do?
A framework-agnostic, git-native standard for defining AI agents
Is Wiki Query safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Wiki Query access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (799d6d0ad18c), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.