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 chicken-noodle-chris/tome --skill querygit clone --depth 1 https://github.com/chicken-noodle-chris/tomeWrote 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/chicken-noodle-chris/tome/query)<a href="https://agentmods.dev/skills/chicken-noodle-chris/tome/query"><img src="https://agentmods.dev/badge/skills/chicken-noodle-chris/tome/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/chicken-noodle-chris/tome/query"><img src="https://agentmods.dev/badge/skills/chicken-noodle-chris/tome/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 | $0.00023 | $0.00770 |
| Opus 5 | $0.00012 | $0.00385 |
| Sonnet 5 | $0.00005 | $0.00154 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Optional input: the question, and optionally a project to scope it to.
Conventions live in wiki/SCHEMA.md; scripts/tome.py (tome help) scaffolds any page this
produces. tome is on PATH in Bash (the plugin's SessionStart hook puts it there) — just
run tome <cmd>; if it's ever not found, fall back to python "$TOME_PLUGIN_ROOT/scripts/tome.py" <cmd>. It resolves which vault to act on via --vault
/ walking up from cwd / VAULT_ROOT, and bare paths like wiki/index.md are relative to
the vault root, not the plugin root.
-
Prime yourself. Read
wiki/SCHEMA.mdif you haven't this session — some wikis declare query-specific conventions that override the default flow below. -
Read the index first. Start at
wiki/index.md(or the relevant shard underwiki/indexes/if sharded). Build a short candidate list from the one-line summaries — be selective; reading dozens of pages to answer one question means the index isn't doing its job. -
Fall back to search only if the index doesn't surface good candidates.
tome search "query terms" --top 10(BM25 over frontmatter + body;--type,--tag,--sincefilters;--backlinks <slug>for inbound-link lookups). Fallback, not the default — index-first is cheaper and more interpretable when it works. -
Read the candidates in full. Note
[[wikilinks]]to other pages as you go — pre-curated leads — but don't recursively chase every link. If a page cites a source page and the answer hinges on exactly what that source said, read the source page too; only go back toraw/itself if the wiki's summary is clearly insufficient. -
Synthesize the answer, cited. Write it in your own words with
[[wikilink]]citations to every page you drew on. If the wiki holds contradicting claims, surface the contradiction rather than silently picking one. If the wiki has nothing relevant, say so plainly — don't confabulate — and suggest what to ingest to fill the gap. -
Offer to file the answer back. Default to offering when the answer represents real connection-making (a comparison, a synthesis across pages, an answer to a recurring question) — not for a trivial one-line lookup. On approval:
tome new synthesis <slug> --project <name> --title "T" --desc "...", body = the answer, cite the pages consulted. -
Log it.
tome log query "<question summary>", andtome sync -m "..."if anything was filed back (a read-only query still logs; the log line rides along with the next sync).
Anti-patterns: reading the whole wiki "to be safe" instead of trusting (or fixing) the index; citing the wiki without chaining back to a raw source for a claim the user might need to verify; filing back answers that don't earn a permanent page; inventing an answer when the wiki is silent.
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.
- 9d ago First seen · 49 lines · 23 tokens per session scan A bbedaa1f7ab2
query is a skill published in the GitHub repository chicken-noodle-chris/tome (6 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 770 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…