bench-model

bench-model is a skill for Claude Code, Codex from MarkusNeusinger/cite-citadel. It costs 306 tokens per session (2,536 once invoked), scanned C, original, MIT.

A benchmark for measuring how well a selected language model or agent command-line tool creates a cited wiki from a source collection. Unlike a pipeline test, it compares the model while keeping the wiki-building process fixed.

In plain words
What is it for?
Use it to run model comparisons, grade wiki-building results, inspect structural checks and citations, and analyze errors such as missed updates, contradictions, or false claims.
Why use it?
It shows whether differences in wiki quality come from the chosen model, including missed contradictions or incorrect claims, rather than from changes to the processing pipeline.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/markusneusinger/cite-citadel/bench-model
Any agent
npx skills add MarkusNeusinger/cite-citadel --skill bench-model
Clone the repo
git clone --depth 1 https://github.com/MarkusNeusinger/cite-citadel

Made for: Claude Code, Codex.

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 bench-model

README.md
[![agentmods](https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/bench-model.svg)](https://agentmods.dev/skills/markusneusinger/cite-citadel/bench-model)
Your own site
<a href="https://agentmods.dev/skills/markusneusinger/cite-citadel/bench-model"><img src="https://agentmods.dev/badge/skills/markusneusinger/cite-citadel/bench-model.svg" alt="Measured on agentmods" height="20"></a>
Per session 306 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,536 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00306 $0.02536
Opus 5 $0.00153 $0.01268
Sonnet 5 $0.00061 $0.00507
Haiku 4.5 $0.00031 $0.00254

Measured 3d ago against content hash 54e4ffde665a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

bench-model 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 3d 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.

throwaways (`rm -rf`), kept only while a `--baseline` comparison still needs them.
.claude/skills/bench-model/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bench a model on wiki creation

Usage: bench-model <corpus> <model> [--cli claude|copilot|agy] [--baseline SANDBOX] [--grade-only SANDBOX]

Everything sandbox/grading-related follows verify-corpus (read its SKILL.md first — sandbox recipe, phase 1 structural gates, phase 2 retrieval-first grading, the creation-vs-retrieval miss matrix, the gotchas). This skill changes the question: not "does the pipeline still work?" but "how well does THIS model drive it?" — so the model is the variable, the grade gains a discriminative tier, and the output is a comparison, not just pass/fail.

Reference points (2026-07 audit, beverages, 14 sources)

claude-sonnet-5 claude-haiku-4-5
pace ~7.5 min/source ~3 min/source (~2.5× faster)
structural gates check+lint clean check+lint clean
ground-truth grade no wiki-defects on its subset 7 wiki-defects
judgment failures none observed 3 uncaught contradictions; a planted-false claim ("coffee loses caffeine with age") adopted as unqualified wiki-voice truth; partial 2024→2026 supersession

The pattern to test for: cheap models produce structurally valid, well-cited pages at speed but miss judgment-heavy work — surfacing contradictions, quarantining suspicious claims, temporal supersession, open-points discipline. Structural gates alone will NOT separate models.

Mode A — build with the model under test

Per verify-corpus's sandbox recipe, with the model pinned; run ingest in the background (a foreground shell call gets killed by per-command timeouts long before a full corpus finishes):

REPO="$(git rev-parse --show-toplevel)"
SANDBOX="$(mktemp -d)/bench-<corpus>-<model>"
uv run python -m citadel init "$SANDBOX"
cat > "$SANDBOX/.env" <<EOF
CITADEL_LLM_CLI=claude                 # or copilot / agy — the seam for open/local models
CITADEL_INGEST_MODEL=<model>
CITADEL_LLM_LOG_DIR=$SANDBOX/logs
CITADEL_RAW_DIR=$REPO/corpora/<corpus>/raw
EOF
# sanity-check the model id first (cheap):  claude --model <model> -p "Reply with exactly: ok"
CITADEL_WORKSPACE="$SANDBOX" uv run python -m citadel ingest --quiet &   # background; poll:
uv run python -c "import json;print(len(json.load(open('$SANDBOX/wiki/.citadel_ingested.json'))['sources']))"

Read the full file on GitHub · 149 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. 3d ago First seen · 149 lines · 306 tokens per session scan C 54e4ffde665a

Subscribe to this mod's changes

bench-model is a skill published in the GitHub repository MarkusNeusinger/cite-citadel (2 stars, last pushed 5d ago), licensed MIT. It adds 306 tokens to every session and 2,536 once invoked, about $0.0015 per session on Opus 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.

Related

Other skills, from other repositories

design-debt-audit

Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).

Owl-Listener/designer-skills · 59 tokens

design-impact-reporting

Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).

Owl-Listener/designer-skills · 44 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

survey-design

Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).

Owl-Listener/designer-skills · 47 tokens

localization-design

Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).

Owl-Listener/designer-skills · 49 tokens

motion-system

Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).

Owl-Listener/designer-skills · 48 tokens