answer-from-corpus

answer-from-corpus is a skill for Claude Code from chrisgagne/grounded-forge. It costs 76 tokens per session (4,567 once invoked), scanned A, original, MIT.

A workflow for answering questions from a prepared source collection instead of relying only on general knowledge. It classifies the question and retrieves task-specific source summaries with evidence markers and attribution.

In plain words
What is it for?
It is for answering questions from a compiled corpus, finding named references, diagnosing issues, and combining evidence across task-specific summaries.
Why use it?
It helps answers stay tied to the material in the collection and makes unsupported claims easier to identify. Different retrieval paths handle direct lookups, diagnostics, and broader combinations of sources.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the grounded-forge plugin — 12 skills, 2 agents, 1 hook shipped together

Good fit It is for answering questions from a compiled corpus, finding named references, diagnosing issues, and combining evidence across task-specific summaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisgagne/grounded-forge/answer-from-corpus
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 chrisgagne/grounded-forge --skill answer-from-corpus
Clone the repo
git clone --depth 1 https://github.com/chrisgagne/grounded-forge

Made for: Claude Code.

Or install grounded-forge, the plugin that ships this one along with the rest of its 12 skills, 2 agents, 1 hook.

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 answer-from-corpus

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/answer-from-corpus.svg)](https://agentmods.dev/skills/chrisgagne/grounded-forge/answer-from-corpus)
Your own site
<a href="https://agentmods.dev/skills/chrisgagne/grounded-forge/answer-from-corpus"><img src="https://agentmods.dev/badge/skills/chrisgagne/grounded-forge/answer-from-corpus.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,567 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 $0.00076 $0.04567
Opus 5 $0.00038 $0.02284
Sonnet 5 $0.00015 $0.00913
Haiku 4.5 $0.00008 $0.00457

Measured 7d ago against content hash 11019b4aefef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

answer-from-corpus 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 7d 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.

.claude/skills/answer-from-corpus/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Answer from corpus

Source-grounded answer protocol for any substantive question the corpus may cover. Distillations are the source-grounded product: each carries paraphrased prose with parenthetical attribution and verbatim blockquotes copied from already-audited Pass D passages, with evidence markers ([V] / [AP] / [AR] / [AE] / [BT]) preserved. The reference tier (light + deep) stays at corpus level as the audit-of-record but does not travel with the compiled app; this skill reads distillations only.

Invoke this skill to operationalise the bundled CLAUDE.md's grounding directive: CLAUDE.md sets the principle (search before reasoning from priors; cite or admit guessing), this protocol runs it as executable steps — shape-classification, traceability, citation density, corpus breadth.

Procedure

Path convention. Every path in this skill is written from the app's perspective: ./distillations/{task}/, ./concept-index.json, ./lens-index.json, ./slug-table.json. The distillations directory and the runtime JSON indexes sit at the app root.

--corpus {slug} flag. When the operator passes --corpus my-corpus in the invocation (e.g., /answer-from-corpus --corpus demo What is a definition of done?), the skill targets that named corpus's bundled artefacts. Default: the only corpus the app ships.

Step 0: Classify the query shape

Before any reads, classify the question:

  • Named lookup. The user names a specific framework, author, work, or concept ("what does TC 25-20 say about the AAR cycle", "tell me about Dekker's Just Culture as treated in the corpus"). Signal: the answer reduces to what does this one source say. → Protocol N.
  • Diagnostic. The user describes a situation that needs reference-mediated guidance ("how do I handle a stakeholder conflict", "I need to make a decision under uncertainty"). Signal: there's a task domain in play, and the corpus has distillations for it. → Protocol D.
  • Synthesis. The user asks what the corpus says about a broad topic ("what is Agile", "what does the corpus say about employee motivation"). Signal: the answer benefits from breadth across multiple authors/traditions and the question is not a named lookup or in-task diagnostic. → Protocol S.

Read the full file on GitHub · 205 lines

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. 7d ago First seen · 205 lines · 0 tokens per session scan A 11019b4aefef

Subscribe to this mod's changes

answer-from-corpus is a skill published in the GitHub repository chrisgagne/grounded-forge (7 stars, last pushed 17d ago), licensed MIT. It adds 76 tokens to every session and 4,567 once invoked, about $0.0004 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.