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.
git clone --depth 1 https://github.com/eddiebelaval/squireWrote 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/commands/eddiebelaval/squire/kb-query)<a href="https://agentmods.dev/commands/eddiebelaval/squire/kb-query"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-query/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/commands/eddiebelaval/squire/kb-query"><img src="https://agentmods.dev/badge/commands/eddiebelaval/squire/kb-query.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 | $0.00000 | $0.01362 |
| Opus 5.5 | $0.00000 | $0.00545 |
| Sonnet 5.5 | $0.00000 | $0.00272 |
| Haiku 4.5 | $0.00000 | $0.00136 |
Grade A, and why
kb-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 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kb-query -- Knowledge Base Query
You answer questions against id8Labs knowledge bases, citing sources with Obsidian wikilinks.
Arguments: $ARGUMENTS
Route by Arguments
Parse $ARGUMENTS:
| Input | Action |
|---|---|
<question> |
Query the most relevant KB (auto-detect from question content) |
<question> --kb <name> |
Query a specific KB |
<question> --all |
Query across all KBs (federated) |
<question> --save |
Save the answer to the KB's output/ directory |
<question> --kb <name> --save |
Query specific KB and save |
<question> --slides |
Output answer as Marp slide deck |
<question> --slides --save |
Generate slides and save to output/ |
list |
List all registered KBs with descriptions and tags |
| (empty) | List all registered KBs |
Flags can be combined: --all --save, --kb research --save, --all --slides --save
Setup
- Read
~/Development/id8/knowledge/manifest.json - Read the skill reference:
~/.claude/skills/knowledge/SKILL.md
Query Process
Step 1: Select Target KBs
- If
--kb <name>: use only that KB - If
--all: use all KBs in manifest - If no flag: read question, match against KB tags in manifest, select the most relevant 1-2 KBs
Step 2: Load Indexes
For each target KB:
- Read
{kb}/wiki/_index.mdto understand what articles exist - Scan section headers and article descriptions to identify relevant articles
Step 3: Read Relevant Articles
Based on the question:
- Identify which concept, source, and connection articles are relevant
- Read those articles (use Glob to find files if needed)
- For extended KBs (research): also check registries (findings, contradictions, open-questions)
- For mirror KBs (memory): read the linked topic files
Be selective. Don't read the entire KB. Read the index, identify 3-8 relevant articles, read those.
Step 4: Synthesize Answer
Answer the question using information from the articles:
- Cite sources using
[[wikilinks]](e.g., "According to [[concepts/dark-mode-native]], ...") - If cross-KB query: clearly attribute which KB each insight comes from
- If information is insufficient: say so and suggest what raw sources might help
- Be concise but thorough
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 · 197 lines · 0 tokens per session scan A b2ae7aa66173
kb-query is a command published in the GitHub repository eddiebelaval/squire (21 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,362 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 2026-09-03.
Other commands, from other repositories
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
slides
A presentation-making command that creates slides from a topic using Manus Slides, with 24 stated visual styles. It can export the result as PPTX, PDF, or HTML files.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.