Borrowing it
Nothing to install: this file belongs to P1-103n1x/bab-ilu. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/P1-103n1x/bab-ilu/v2.2-oss-public/.claude/skills/ask/SKILL.mdgit clone --depth 1 https://github.com/P1-103n1x/bab-iluWrote 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/p1-103n1x/bab-ilu/ask)<a href="https://agentmods.dev/skills/p1-103n1x/bab-ilu/ask"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/ask/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/p1-103n1x/bab-ilu/ask"><img src="https://agentmods.dev/badge/skills/p1-103n1x/bab-ilu/ask.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 | $0.00093 | $0.02035 |
| Opus 5 | $0.00046 | $0.01018 |
| Sonnet 5 | $0.00019 | $0.00407 |
| Haiku 4.5 | $0.00009 | $0.00203 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ask — Lens-aware vault query
Lens awareness (v2.1)
/ask traverses the same graph every lens writes, but what counts as
a good answer varies sharply by lens — aesthetic answers cite
motifs and Panofsky layers, engineering answers cite patterns and
incident cross-refs, zettelkasten answers cite Bloom-indexed notes
and concept-clusters.
Runtime wiring:
- Resolve the active lens via
tools/lens_loader.load_lens(); honor--lens <id>override. Missing lens is fatal. - Inject
tools.lens_context.active_lens_preamble()at the top of the answer-synthesis LLM call. This is the single most important step — without the lens's judgment rules in context, the synthesis falls back to generic "encyclopedia voice" and loses lens identity. - Prefer entries whose frontmatter
lens:field matches the active lens id. Cross-lens entries are visible but flagged in the answer ("cited from a different lens's index — may not use current vocabulary"). - Use
lens.entity_modelto type search results: "show me all tier_1_cluster under active lens" maps to searching the{tier_1_cluster}type.
Retrieval order (lens-aware)
For each candidate query term, search in this priority:
wiki/syntheses/*.md— filed-back answers from prior/asksessions (K1, Sprint 4). Lens-filtered. Substring match on frontmatterquestion:ortitle:. Highest priority because these are curated bundles representing the wiki's compounding knowledge, per Karpathy原教旨 (PRD §0.5.4).- Exact title match in frontmatter of
tier_0 / tier_1_atom / tier_1_clusterfiles under the active lens aliases:matchoriginal_terms:match (bilingual queries).agent/todos/<tier_1_cluster>-candidates.md(A4 gap_runner output; unaccepted candidates are still knowledge)wiki/questions/*.md(A4 bridge-candidate stubs; open questions ARE answers when the asker wants gaps)grep -iacross markdown body for unique phrases
Steps 4-5 are new in v2.1 — they surface the system's own uncertainty as part of the answer, lens-neutral (every lens benefits from "here's what we don't know yet").
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 · 207 lines · 93 tokens per session scan A a7ffaf0e3250
ask is a skill published in the GitHub repository P1-103n1x/bab-ilu (11 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 2,035 once invoked, about $0.0005 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 2026-08-30.
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…