What is verify-corpus?

An end-to-end test and grading tool for the Citadel ingest and curate pipelines. It loads supplied test collections, checks the resulting wiki structure, and compares facts with a hidden answer key.

Use it to verify named corpora such as beverages, kelvarra, or pemberley, run grading-only checks, or test all shipped corpora.

It shows whether the full pipeline handles importing, reconciling, deleting, forcing updates, and correcting known defects without damaging valid pages.

How MarkusNeusinger/cite-citadel configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to MarkusNeusinger/cite-citadel. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/MarkusNeusinger/cite-citadel/main/.claude/skills/verify-corpus/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/MarkusNeusinger/cite-citadel

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/verify-corpus/github.svg)](https://agentmods.dev/skills/markusneusinger/cite-citadel/verify-corpus)

Your own site

<a href="https://agentmods.dev/skills/markusneusinger/cite-citadel/verify-corpus"><img src="https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/verify-corpus/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/markusneusinger/cite-citadel/verify-corpus"><img src="https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/verify-corpus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 555 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 11,871 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00555	$0.11871
Opus 5.5	$0.00222	$0.04748
Sonnet 5.5	$0.00111	$0.02374
Haiku 4.5	$0.00056	$0.01187

Measured 13d ago against content hash 3c32b831bda0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

verify-corpus scanned grade C with 1 finding 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 13d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

survives the `rm -rf`.

.claude/skills/verify-corpus/SKILL.md · 643 lines

How it starts

The opening of the file, as written. The whole thing — 643 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify a corpus end-to-end

Ten shipped corpora, each a corpora/<name>/ bundle (raw/, sometimes stages/ or a materializable repo tree, a README.md) plus a hidden answer key at .claude/skills/verify-corpus/<name>/ground-truth.md. The ingest agent never sees the key — it lives outside the corpus, and Mode A points CITADEL_RAW_DIR at the corpus raw/ only (defense in depth). This skill runs the real pipeline into a sandbox, then grades that sandbox wiki against the key. Grading is a two-phase FACTS-style gate: phase 1 = citadel check + lint exit 0 (structural eligibility); phase 2 = answer-key content grading.

Modes A/B grade the ingest lifecycle. Mode C (below) grades the curate lifecycle end-to-end — it seeds known defects into a sandbox, proves the offline detectors flag exactly them, then runs real curate sessions and grades that the model FIXES them without breaking valid pages.

corpus	what it stresses	sandbox note	ground-truth
`beverages`	organized / links / provenance on a messy coffee+tea corpus; the showcase wiki	10 files, one pass each	`.claude/skills/verify-corpus/beverages/ground-truth.md`
`kelvarra`	the hardest guarantee: a fictional world stated wrong about reality, kept as-stated and cited, never corrected	7 files, one pass each	`.claude/skills/verify-corpus/kelvarra/ground-truth.md`
`leuchtfeuer`	reconcile / delete / force across 3 dated waves; temporal supersession; German→English; opinions & style	3 waves (see the wave protocol)	`.claude/skills/verify-corpus/leuchtfeuer/ground-truth.md`
`pemberley`	large-source multi-segment chunking; relationship extraction; in-novel misinformation; narrative supersession	one ~730k-char file → ~18 segments, HOURS — set a LONG timeout and force chunking (see the pemberley note)	`.claude/skills/verify-corpus/pemberley/ground-truth.md`
`injection-resistance`	embedded adversarial instructions treated as content, never executed; real facts still extracted	3 files, 3 quick sessions	`.claude/skills/verify-corpus/injection-resistance/ground-truth.md`
`clockwork`	a whole git repo folded in as ONE digest (`kind=repo`), then a second commit driving `kind=repo-reconcile`; folder-keyed provenance; one documented default superseded	materialize the repo + 2 commits (see the clockwork note)	`.claude/skills/verify-corpus/clockwork/ground-truth.md`
`flurfunk`	informal genres (chat / social / interview / application / forum); attribution ("X said Y" ≠ "Y is true"), in-thread reversal, a quote-tweet negative row, CV timeline, partial lists, a source to-do, a folder-note caveat	11 files (incl. a `retros/` folder note + 3 siblings), one pass each	`.claude/skills/verify-corpus/flurfunk/ground-truth.md`
`gazette`	PDF sources: `CITADEL_PDF_MODE` text-vs-images (a figure-only number + an image-only page), the publications genre, references-are-not-sources, page locators, chunked-window edges, a garbled text layer read from the page image, letterhead kept out of the facts, and dedup-by-basename (`.ics` behind its PDF twin)	9 files (7 PDFs + 1 md + 1 `.ics`; 8 ingested, the `.ics` a skipped duplicate); three runs (text, images, then a chunked run — see the gazette note)	`.claude/skills/verify-corpus/gazette/ground-truth.md`
`kontor`	binary Office documents (OOXML .pptx/.docx/.xlsx + legacy OLE .doc/.ppt/.xls); the Office extraction path, an embedded-chart image delta (CITADEL_IMAGE_SUPPORT), dedup-by-basename, ignore-patterns, source-exclusion enforcement (`CITADEL_IGNORE_PATTERNS=+private`); the usual judgment traps	13 files (9 Office + 3 junk + 1 excluded `private/` text file); two runs (images off then on — see the kontor note)	`.claude/skills/verify-corpus/kontor/ground-truth.md`
`werkhof`	uniform enumerable sources (a 28-machine register, a 20-code fault catalogue, a 15-customer CSV): `Registry` completeness (no entry compressed away), per-row citations + locators, promotion past the granularity floor, a status supersession, near-miss keys	4 files, one pass each	`.claude/skills/verify-corpus/werkhof/ground-truth.md`

Read the full file on GitHub · 643 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago Changed · +38 lines · +16 tokens per session 3c32b831bda0
2mo ago First seen · 605 lines · 539 tokens per session scan C 885339d3b88d

Subscribe to this mod's changes

verify-corpus is a skill published in the GitHub repository MarkusNeusinger/cite-citadel (3 stars, last pushed 15d ago), licensed MIT. It adds 555 tokens to every session and 11,871 once invoked, about $0.0022 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI E2E testing Testing agentic ai-tools citations claude cli knowledge-base

verify-corpus next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
verify-corpusMarkusNeusinger/cite-citadel	Skill	3	15d ago	MIT	C	555	Claude Code
vue-component-testingsoulcodex/agentic	Skill	10	7d ago	MIT	A	79	Claude Code, Codex
e2e-testingQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	94	Claude Code, Codex
terminal-captureQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	66	Claude Code, Codex
tmux-real-user-testingQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	98	Claude Code, Codex
agent-reproduce-alignQwenLM/qwen-code	Skill	29k	yesterday	Apache-2.0	A	62	Claude Code, Codex
test-appmendixlabs/mxcli	Skill	137	yesterday	Apache-2.0	A	86	Claude Code

cite-citadel: Skill for Claude Code