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/voxpelli/vp-claude/knowledge-asknpx skills add voxpelli/vp-claude --skill knowledge-askgit 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-ask)<a href="https://agentmods.dev/skills/voxpelli/vp-claude/knowledge-ask"><img src="https://agentmods.dev/badge/skills/voxpelli/vp-claude/knowledge-ask.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 | $0.00142 | $0.01847 |
| Opus 5 | $0.00071 | $0.00924 |
| Sonnet 5 | $0.00028 | $0.00369 |
| Haiku 4.5 | $0.00014 | $0.00185 |
Grade A, and why
knowledge-ask 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 5d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Ask
Answer a freeform question by searching the Basic Memory knowledge graph, loading relevant notes, traversing 1-hop neighbors, and synthesizing a cited answer. Each answer includes a confidence tier (Direct, Partial, or No Coverage) so the user knows how much the graph actually covers.
Read-only -- never writes or modifies notes. When coverage is incomplete, suggests
/intel or /knowledge-gaps to fill the gap.
Arguments
The user provides a topic or question after the skill invocation:
| Form | Example |
|---|---|
| Topic phrase | /knowledge-ask fastify error handling |
| Natural language question | /knowledge-ask how does pino redaction work? |
| Concept | /knowledge-ask IndieWeb |
| Package identifier (with prefix) | /knowledge-ask npm:undici |
| Tool identifier (with prefix) | /knowledge-ask brew:ripgrep |
| gh CLI extension (with prefix) | /knowledge-ask gh:meiji163/gh-notify |
Prefixed identifiers (npm:, crate:, brew:, action:, gh:, etc.) trigger
a fast existence check via list_directory in addition to the hybrid search.
Edge Cases
- No results -- assign "No Coverage" confidence. Report "Basic Memory has no
notes matching this question." Suggest
/intel <pkg>if the query looks like a package or tool name. - BM unavailable -- report the error and suggest trying again later. The PostToolUseFailure hook covers BM write-tool errors only; read-tool failures (search_notes, read_note, build_context) surface as raw error strings.
- Ambiguous query -- if
search_notesreturns results spanning 3+ unrelated topics, pick the best-matching cluster and note "Results also touched [other topics] -- narrow your query for those." - Package/tool not in BM -- if a prefixed query (e.g.,
npm:undici) has nolist_directorymatch and no search results, report "No note found fornpm:undici." and suggest/intel undicito create it. - Very broad query -- if the query maps to an entire ecosystem directory
(e.g., "what do I know about npm packages"), use
list_directory(dir_name="npm", depth=1)to report directory-level counts rather than loading individual notes. Suggest/knowledge-primefor project-scoped overviews or/knowledge-gapsfor coverage audits. - Schema notes in results -- exclude notes with titles starting with
schema/from the answer synthesis. These are structural definitions, not knowledge content.
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.
- 5d ago First seen · 195 lines · 142 tokens per session scan A dda7a1de3a43
knowledge-ask is a skill published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 8d ago), licensed MIT. It adds 142 tokens to every session and 1,847 once invoked, about $0.0007 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…
sibling-sync
Bilateral SYNERGY/UPSTREAM reconciliation across sibling projects. Use when the user wants to sync sibling SYNERGY/UPSTREAM files, compare both sides to surface drift, find reciprocation gaps (entries here but not there, or vice versa), flag stale-aligned rows, detect status drift across sides, surface friction the…
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…
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…