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/rjroy/vibe-garden/querynpx skills add rjroy/vibe-garden --skill querygit clone --depth 1 https://github.com/rjroy/vibe-gardenWrote 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/rjroy/vibe-garden/query)<a href="https://agentmods.dev/skills/rjroy/vibe-garden/query"><img src="https://agentmods.dev/badge/skills/rjroy/vibe-garden/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 | $0.00053 | $0.00745 |
| Opus 5 | $0.00026 | $0.00373 |
| Sonnet 5 | $0.00011 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Query
Answer a question using the project wiki and work artifacts. Cite every source. Offer to persist the answer as a synthesis page.
Gathering sources
Read the field-guide index first. Prefer .lore/reference/index.md; if it does not exist, read .lore/reference/index.html. Scan all listed pages to identify which are relevant to the question. Relevance is broad — include any page whose subject could bear on the answer, even indirectly.
Read every candidate page in full. Candidate pages may be Markdown or HTML. For HTML pages, use meta tags as metadata and visible body content as the page body. Then scan .lore/work/ for supported source documents (.md and .html specs, designs, retros, plans, research) that may contain context not yet extracted into the wiki. Use judgment: if the question is about a decision, check plans and specs. If it's about what broke, check retros. If it's about how something works, check architecture and research documents.
If no relevant material exists, say so. Don't synthesize an answer from general knowledge when the question is asking what this project specifically decided or learned.
Answering
Give a direct answer, then the supporting evidence. If sources conflict, name the conflict and both positions — don't arbitrate silently.
After the answer, list every file cited. Use the file path as the identifier. Example:
Sources:
.lore/reference/auth-flow-decision.md,.lore/work/specs/auth-spec.md
Saving as synthesis
After delivering the answer, ask whether to save it as a synthesis wiki page. If the user accepts:
Write a Markdown page at .lore/reference/[descriptive-kebab-name].md. If the wiki is stratified into category directories (the index will have a "Layout" section), write the page into the best-fitting existing category directory instead of the root. Use YAML frontmatter:
---
title: Precise noun-first description of what the synthesis answers
date: YYYY-MM-DD
status: current
tags: [kebab-case, terms, subject, domain, question-type]
fg-type: synthesis
fg-sources: [relative/path/to/source1.md, relative/path/to/source2.md]
fg-status: current
---
# Precise noun-first description of what the synthesis answers
<!-- body in Markdown -->
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.
- 6d ago First seen · 53 lines · 53 tokens per session scan A 6895d919aff0
query is a skill published in the GitHub repository rjroy/vibe-garden (6 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 745 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
bottle
Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased…
pace-learn
Use when user says "/pace-learn", "经验", "知识库", "pattern", "lessons learned", "学到了什么", or auto-invoked after CR merge, gate failure recovery, or human rejection. NOT for iteration retrospectives or metrics (use /pace-retro). NOT for concept explanations (use /pace-theory).
recursive-spine-pollinate
Use when something just proved itself in real work and should be carried to other projects — captures it as a pollen record in the builder's hive (registry file + paired issue), or, in pull mode, reads every configured hive and offers relevant transplants into the current repo, recording each transplant back onto the…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
cross-session-handoff
Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.