fixture-tricky

fixture-tricky is a skill for Claude Code from grahama1970/agent-skills. It costs 43 tokens per session (1,522 once invoked), scanned A, original, no licence file.

A test-content generator for PDFs that creates difficult cases for document extractors. Its examples include misleading tables, malformed tables, damaged text, and layout traps.

In plain words
What is it for?
Use it to create adversarial PDF fixtures and add new edge cases found in real documents.
Why use it?
It exposes extraction failures before real users encounter them. This helps test whether a PDF parser handles unusual layouts and text correctly.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to create adversarial PDF fixtures and add new edge cases found in real documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/grahama1970/agent-skills/fixture-tricky
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 grahama1970/agent-skills --skill fixture-tricky
Clone the repo
git clone --depth 1 https://github.com/grahama1970/agent-skills

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.

agentmods badge for fixture-tricky

README.md
[![agentmods](https://agentmods.dev/badge/skills/grahama1970/agent-skills/fixture-tricky/github.svg)](https://agentmods.dev/skills/grahama1970/agent-skills/fixture-tricky)
Your own site
<a href="https://agentmods.dev/skills/grahama1970/agent-skills/fixture-tricky"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/fixture-tricky/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 fixture-tricky

Your own site · 80×15
<a href="https://agentmods.dev/skills/grahama1970/agent-skills/fixture-tricky"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/fixture-tricky.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,522 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 unknown 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 $0.00043 $0.01522
Opus 5 $0.00022 $0.00761
Sonnet 5 $0.00009 $0.00304
Haiku 4.5 $0.00004 $0.00152

Measured 9d ago against content hash 7b5990f0440f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fixture-tricky 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.

The scan reads SKILL.md. This mod also ships 9 executable files (gen_app.py, gen_cli.py, gen_generators.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/fixture-tricky/SKILL.md · 208 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 9d ago First seen · 208 lines · 43 tokens per session scan A 7b5990f0440f

Subscribe to this mod's changes

fixture-tricky is a skill published in the GitHub repository grahama1970/agent-skills (6 stars, last pushed today), with no licence file. It adds 43 tokens to every session and 1,522 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

document-query

Read, extract or compare PDFs, Office files, URLs and large text; OCR when vision fails.

agent0ai/agent-zero · 23 tokens

inspect-repair

Run a free deterministic quality report on ANY PowerPoint file (yours or generated elsewhere) and optionally auto-repair it. Use when the user asks to check/lint/QA/review a pptx, find broken slides, fix overflowing or hidden text, clean up a deck before sending, or verify a generated deck. Uses the SlideForge REST…

smartdatabrokers/slideforge-mcp · 87 tokens

Chat with PDF

Answer questions about PDF content, summarize, and extract information.

claude-office-skills/skills · 15 tokens

yellow-sheet-corpus

Run the Yellow Sheet chain end to end against ANY matter, from the original PDFs, and read the result honestly. Use whenever someone asks what has been tested end to end, whether a matter produces a usable sheet, how to onboard a NEW matter, or asks to re-run after a code change. Carries the intake mechanism that…

shawnclybor/clybor-claude-tooling · 173 tokens

skill-doc-delivery

Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.

nyldn/claude-octopus · 29 tokens