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 voxpelli/vp-claude --skill knowledge-gardengit clone --depth 1 https://github.com/voxpelli/vp-claudeWrote 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/voxpelli/vp-claude/knowledge-garden)<a href="https://agentmods.dev/skills/voxpelli/vp-claude/knowledge-garden"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/knowledge-garden/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/voxpelli/vp-claude/knowledge-garden"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/knowledge-garden.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 | $0.00152 | $0.02523 |
| Opus 5 | $0.00076 | $0.01262 |
| Sonnet 5 | $0.00030 | $0.00505 |
| Haiku 4.5 | $0.00015 | $0.00252 |
Grade A, and why
knowledge-garden 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 8d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Garden
Audit Basic Memory notes for structural and quality issues, then report
actionable, copy-paste-ready findings. Read-only — never writes or modifies
notes. Fixes are handed off to /knowledge-maintain.
This skill is the scoped, interactive sibling of the knowledge-gardener agent.
It owns the common case — auditing a handful of named notes inline in the main
session — and delegates the heavy, graph-wide sweep to the agent so the full
audit's hundreds of note reads stay out of the main context window.
Arguments
The user names the notes or topics to audit after the invocation:
| Form | Example |
|---|---|
| One note title | /knowledge-garden npm-fastify |
| Several notes | /knowledge-garden npm-umzeption npm-umzug |
| Prefixed identifier | /knowledge-garden brew:ripgrep |
| Topic phrase | /knowledge-garden the IndieWeb concept notes |
| No arguments | /knowledge-garden → whole-graph audit (delegated) |
1. Decide venue (scoped inline vs delegate)
This is the first and most important step. Classify the request:
Delegate to the agent when the request is graph-wide — any of:
- No arguments are provided.
- The argument is a whole-graph phrase: "my knowledge graph", "the whole graph", "everything", "all notes", "full audit", "--full", "graph health".
- The request implies graph-wide checks the inline path cannot do efficiently: schema drift across a whole type, version drift across ecosystems, cross-project scope leak, orphan detection across the entire graph, tag alignment.
To delegate, launch the read-only auditor and stop: call
Agent(subagent_type="knowledge-gardener", description="Full graph health audit", prompt="<the user's original request, verbatim>")
— i.e. pass a description summarizing the audit as "Full graph health
audit" and a prompt that is the user's original request, verbatim.
Relay the agent's report. Do not also run the inline path. If the Agent
call fails or returns no usable report (unknown subagent type, error payload,
or empty output — the knowledge-gardener agent may not be installed), say so
explicitly: name the failure, do not fabricate a clean result, and offer to
run the scoped inline path on a named subset as a fallback. Never report a
passing audit you did not actually receive.
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.
- 8d ago First seen · 196 lines · 152 tokens per session scan A a7d99d254883
knowledge-garden is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 11d ago), licensed MIT. It adds 152 tokens to every session and 2,523 once invoked, about $0.0008 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
harden-memories
Audit the bd remember store and recommend which entries to prune, so each one earns its per-session bd prime injection cost. Read-only: it proposes a triage table plus the exact bd forget / migration commands; you run them. Use when bd remember entries have accumulated, feel stale, redundant, or conflicting, or when…
synergy-tracker
Manage cross-project synergy tracking between sibling projects. Use when the user wants to log a shared pattern, a divergence, an extraction candidate, or something a sibling project has that this one doesn't. Also use when the user wants to promote synergy entries to Basic Memory (workflow 5). NOT for upstream…
upstream-tracker
Manage upstream issue tracking for this project. Use when the user wants to log a bug or friction point in a vendor package or npm dependency, review open upstream items, resolve a tracked issue, run a trend review, generate the upstream observations section of a sprint retrospective, promote upstream observations to…
retrospective
Run a sprint retrospective for this project. Use when the user says 'retrospective', 'retro', 'close out the sprint', 'what went well', 'generate retro', or wants to generate a RETRO-NN.md file. Reads UPSTREAM-.md files, recent git history, and conversation context to pre-populate the retrospective. Do NOT use for…
backlog-groomer
Manage the beads backlog for this project. Use when the user wants to review or triage open issues, reprioritize the backlog, identify obsolete issues to close, investigate a topic to inform future work, create new issues from research findings, or enrich an existing issue with external context. Trigger phrases…
swarm-wave
Orchestrate multi-agent development sprints with wave-based parallelism. Use when the user wants to plan a swarm sprint, partition work into file-disjoint waves, map file contention across open issues, run a post-wave quality gate with review agents, manage agent backpressure, run a parallel research wave, or…