agentmods.dev

corpus-ask

corpus-ask is a skill for Claude Code from moliver28/corpus-kb. It costs 55 tokens per session (293 once invoked), scanned A, original, MIT.

A question-answering tool that uses the documents in your corpus and includes citations showing where each answer came from.

In plain words
What is it for?
Use it to ask questions about ingested documents, check the cited file or passage, and identify when the corpus has no matching information.
Why use it?
It helps you find sourced answers in a large set of reports, interviews, transcripts, or research files without reading every file manually.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the corpus-rag plugin — 3 skills, 2 commands, 2 hooks shipped together

not rated 1repo yesterday A scan 55 tokens original MIT

Good fit Use it to ask questions about ingested documents, check the cited file or passage, and identify when the corpus has no matching information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/moliver28/corpus-kb/corpus-ask
View source ↗ moliver28/corpus-kb
Install

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.

Any agent
npx skills add moliver28/corpus-kb --skill corpus-ask
Clone the repo
git clone --depth 1 https://github.com/moliver28/corpus-kb

Made for: Claude Code.

Or install corpus-rag, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 2 hooks.

Wrote 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.

agentmods badge for corpus-ask

README.md
[![agentmods](https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-ask/github.svg)](https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ask)
Your own site
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ask"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-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.

agentmods 80×15 button for corpus-ask

Your own site · 80×15
<a href="https://agentmods.dev/skills/moliver28/corpus-kb/corpus-ask"><img src="https://agentmods.dev/badge/skills/moliver28/corpus-kb/corpus-ask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 293 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00293
Opus 5.5 $0.00022 $0.00117
Sonnet 5.5 $0.00011 $0.00059
Haiku 4.5 $0.00006 $0.00029

Measured yesterday against content hash 170d63f59a94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-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 yesterday.

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.

plugins/corpus-rag/skills/corpus-ask/SKILL.md · 38 lines

What it actually says

Corpus Ask

Answer a question from the user's corpus with citations. The corpus is the documents the user ingested with Corpus-KB.

Steps

  1. Check the question is clear. If it is vague, run a search first:

    corpus-kb search "<topic words>"

    Use the hits to sharpen the question.

  2. Ask the engine:

    corpus-kb ask "<the user's question>"

  3. Read the answer. It arrives with source citations. Report the citations with the answer. Show the file or chunk the citation names.

  4. If the answer says the corpus has no matching content, say that plainly. Do not invent sources. Offer to ingest more files (see corpus-ingest).

Notes

  • The engine must be installed and reachable. Run corpus-rag status to check. See the plugin README for setup help.
  • Degraded mode: without the embedding service the engine still searches with keywords. Answers may miss some sources. Say so when you see the degraded notice in the output.
Changes

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.

  1. yesterday First seen · 38 lines · 55 tokens per session scan A 170d63f59a94

Subscribe to this mod's changes

corpus-ask is a skill published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 293 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-07.

DocumentsPDFResearch
Related

corpus-ask compared with skills from other repositories

corpus-ask next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
corpus-askmoliver28/corpus-kbSkill1yesterdayMITA55Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49k2d agoMITA48Claude Code
foundry-hosted-agent-validationmicrosoft/agent-frameworkSkill15ktodayMITA82Claude Code, Codex
report-to-pdfasgeirtj/system_prompts_leaksSkill71ktodayCC0-1.0A17Claude Code, Codex
pdf-extract-create-workflowHKUDS/OpenSpaceSkill7.9k2d agoMITA22Claude Code, Codex
document-direct-pythonHKUDS/OpenSpaceSkill7.9k2d agoMITA20Claude Code, Codex
pdf-verification-cliHKUDS/OpenSpaceSkill7.9k2d agoMITA19Claude Code, Codex