What is fixture-keeper?

An agent for regenerating and explaining golden fixtures. Golden fixtures are saved expected results that integration tests compare with new output.

Use it when integration tests fail because files in Fixtures or SampleData changed, to regenerate them, review the diff, and rerun the relevant tests.

It helps distinguish a valid change in expected output from a software bug. It refuses to edit expected results merely to make a failing test pass.

How hoangsonww/Diffuse-Native-Apps configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/Diffuse-Native-Apps. 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/hoangsonww/Diffuse-Native-Apps/master/.claude/agents/fixture-keeper.md

Clone the repo

git clone --depth 1 https://github.com/hoangsonww/Diffuse-Native-Apps

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/agents/hoangsonww/diffuse-native-apps/fixture-keeper/github.svg)](https://agentmods.dev/agents/hoangsonww/diffuse-native-apps/fixture-keeper)

Your own site

<a href="https://agentmods.dev/agents/hoangsonww/diffuse-native-apps/fixture-keeper"><img src="https://agentmods.dev/badge/agents/hoangsonww/diffuse-native-apps/fixture-keeper/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/agents/hoangsonww/diffuse-native-apps/fixture-keeper"><img src="https://agentmods.dev/badge/agents/hoangsonww/diffuse-native-apps/fixture-keeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 135 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.

Model	Per session	Once invoked
Fable 5.1	$0.00029	$0.00135
Opus 5.5	$0.00012	$0.00054
Sonnet 5.5	$0.00006	$0.00027
Haiku 4.5	$0.00003	$0.00014

Measured yesterday against content hash 7d6b454eefd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fixture-keeper 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.

.claude/agents/fixture-keeper.md · 16 lines

What it actually says

You maintain Diffuse golden fixtures.

Read skill fixtures.

Run ./Scripts/generate-fixtures.sh.
Read the git diff under Fixtures/.
Explain every changed expected diff in plain language (what the engine now reports, and why that is correct).
Run swift test --parallel --filter DiffuseIntegrationTests.

Refuse to weaken an expected diff to hide a bug. If the new output is wrong, fix the engine, not the fixture.

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.

yesterday First seen · 16 lines · 29 tokens per session scan A 7d6b454eefd2

Subscribe to this mod's changes

fixture-keeper is an agent published in the GitHub repository hoangsonww/Diffuse-Native-Apps (11 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 135 once invoked, about $0.0001 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.

E2E testing Testing android device-monitoring gradle ios ipados jetpack-compose

fixture-keeper next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fixture-keeperhoangsonww/Diffuse-Native-Apps	Agent	11	1mo ago	MIT	A	29	Claude Code
ui-test-writerahmed3elshaer/everything-claude-code-mobile	Agent	66	4mo ago	MIT	A	49	Claude Code
builderkylehughes/apple-platform-build-tools-claude-code-plugin	Agent	59	8mo ago	MIT	A	90	Claude Code
deep-workerkvdm-co-pilot/create-cmp	Agent	0	17d ago	MIT	A	99	Claude Code
mobile-pr-deprecation-scannerAbdallah-Abdelazim/mobile-pr-review-plugin	Agent	1	2mo ago	MIT	A	134	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	100k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code

Diffuse-Native-Apps: Agent for Claude Code