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 atman-33/workhub --skill kb-querygit clone --depth 1 https://github.com/atman-33/workhubWrote 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/atman-33/workhub/kb-query)<a href="https://agentmods.dev/skills/atman-33/workhub/kb-query"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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/skills/atman-33/workhub/kb-query"><img src="https://agentmods.dev/badge/skills/atman-33/workhub/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 | $0.00039 | $0.01278 |
| Opus 5.5 | $0.00016 | $0.00511 |
| Sonnet 5.5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Query — Knowledge Search + Synthesis
Search the workhub vault, synthesize answers from multiple documents, cite sources with wikilinks, and optionally accumulate new insights as vault notes.
Vault map
| Zone | What lives there |
|---|---|
tasks/ |
task board (_ai/index/tasks.json is the fast index) |
projects/NNNN-<name>/ |
per-project notes and deliverables |
knowledge/<topic>/ |
durable reference knowledge by topic |
journal/ |
daily/weekly notes (temporal queries) |
archive/ |
completed/inactive material |
_ai/logs/ |
agent reports and the KB activity log (kb-log.md) |
Usage
/kb-query "list all notes related to kubernetes"
/kb-query "workhub design decisions so far"
/kb-query "documents referencing MyProject"
/kb-query "summary of work in last 2 weeks"
Route Selection
Choose the optimal search path by question type. Do not always start from an index — pick the fastest route.
Inbox Structure Notes
- Treat
inbox/**/README.mdas structural guidance notes for folder usage. - Exclude or de-prioritize them during routine knowledge queries; use them only when the question is about inbox structure or note organization.
Route A: Direct Folder Access
When: Target is clearly in one zone.
"workhub design decisions" → read projects/workhub/ directly
"infra knowledge overview" → read knowledge/_index.md then scan knowledge/infra/
Route B: Tag Cross-Collection
When: Need to gather documents across folders by topic.
"everything about my-project" → search #proj/my-project across vault
"ML optimization related" → search #topic/ml-optimization
Route C: Backlink Traversal
When: Need to find what references a specific document or entity.
"where is MyProject used" → search for [[MyProject]] and "MyProject"
With obsidian CLI: obsidian backlinks file="DocumentName".
Without CLI: Grep for [[DocumentName]] across vault.
Route D: Index + Log Browse
When: Broad overview or temporal queries.
"what happened recently" → read _ai/logs/kb-log.md (last 20 entries) and recent journal/ notes
"project overview" → read projects/_index.md
"task status" → read _ai/index/tasks.json
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 Changed 1bfab3aaa400
- 2mo ago First seen · 159 lines · 39 tokens per session scan A dfcebb24e397
kb-query is a skill published in the GitHub repository atman-33/workhub (3 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 1,278 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
kb-query compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kb-queryatman-33/workhub | Skill | 3 | 2d ago | MIT | A | 39 | Claude Code |
| garden-tendinglinxule/memex-plugin | Skill | 7 | 2d ago | MIT | A | 131 | Claude Code |
| curator-practicelinxule/memex-plugin | Skill | 7 | 2d ago | MIT | A | 153 | Claude Code |
| memo-writinglinxule/memex-plugin | Skill | 7 | 2d ago | MIT | A | 125 | Claude Code |
| recalllinxule/memex-plugin | Skill | 7 | 2d ago | MIT | A | 112 | Claude Code |
| superbrain-distillm3talux/superbrain | Skill | 42 | 2mo ago | MIT | A | 36 | Claude Code |
| trellis-update-specfy-agent/fyagent | Skill | 218 | yesterday | none | A | 40 | Claude Code, Codex |