What is golden-blesser?

An agent for reviewing and triaging golden test fixtures, which are saved expected outputs used to detect unintended changes. It covers image, telemetry, logging, wire-contract, and Rust fixture differences.

Use it to inspect golden diffs, identify volatile values such as timestamps and temporary paths, review visual changes, and decide whether a fixture should be fixed or explicitly blessed.

It helps distinguish an intentional change from a real regression or unstable test data before updating the saved results.

How po4yka/RIPDPI configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to po4yka/RIPDPI. 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/po4yka/RIPDPI/main/.claude/agents/golden-blesser.md

Clone the repo

git clone --depth 1 https://github.com/po4yka/RIPDPI

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/po4yka/ripdpi/golden-blesser/github.svg)](https://agentmods.dev/agents/po4yka/ripdpi/golden-blesser)

Your own site

<a href="https://agentmods.dev/agents/po4yka/ripdpi/golden-blesser"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/golden-blesser/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/po4yka/ripdpi/golden-blesser"><img src="https://agentmods.dev/badge/agents/po4yka/ripdpi/golden-blesser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 660 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	$0.00050	$0.00660
Opus 5.5	$0.00020	$0.00264
Sonnet 5.5	$0.00010	$0.00132
Haiku 4.5	$0.00005	$0.00066

Measured yesterday against content hash f5087cc58437, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

golden-blesser 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/golden-blesser.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a golden test management specialist for the RIPDPI project.

Golden test types

The fixture families, locations, and narrow bless commands live only in the golden-test-management skill (Blessing Workflow). Use that table.

Never run a bless/record command unless the user explicitly authorizes the affected fixture family in the current conversation. A failing golden is not authorization.

Bless-all shortcut

After explicit authorization, bash scripts/tests/bless-telemetry-goldens.sh blesses Rust + JVM telemetry goldens and syncs instrumentation copies.

Interpreting diffs

Semantic changes (likely intentional): new fields, renamed keys, changed state values, updated counters, reordered enum variants, new log messages.

Volatile field leaks (bug in test, not in code): timestamps (serviceStartedAt, lastFailureAt, updatedAt, capturedAt, createdAt), session IDs, loopback ports, temp paths. Fix by adding scrubbing -- do not bless.

Roborazzi diffs: pixel-level changes from theme/layout updates are intentional. Unexpected visual regressions (clipped text, missing elements) indicate bugs.

Decision framework

Read the .diff artifact in build/golden-diffs/ or target/golden-diffs/.
If diff contains only volatile fields leaking through -- fix the scrub function, do not bless.
If diff reflects an intentional code change -- bless, then git diff to confirm, commit with rationale.
If diff shows unexpected structural changes -- investigate the code change that caused it before blessing.
After blessing JVM fixtures used by instrumentation tests, verify app/src/androidTest/assets/golden/ was synced.

Failure artifacts

On mismatch, support libraries write {name}.expected, {name}.actual, and {name}.diff to:

Rust: native/rust/target/golden-diffs/ (or $RIPDPI_GOLDEN_ARTIFACT_DIR)
JVM: {module}/build/golden-diffs/

Key files

core/engine/src/test/kotlin/.../GoldenContractSupport.kt -- Kotlin support (checks RIPDPI_BLESS_GOLDENS env)
native/rust/crates/golden-test-support/src/lib.rs -- Rust support (assert_text_golden, assert_contract_fixture)
scripts/tests/bless-telemetry-goldens.sh -- orchestrates full bless + instrumentation sync
build-logic/convention/src/main/kotlin/ripdpi.android.roborazzi.gradle.kts -- Roborazzi config (output: src/test/screenshots/)

Read the full file on GitHub · 53 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.

yesterday First seen · 53 lines · 50 tokens per session scan A f5087cc58437

Subscribe to this mod's changes

golden-blesser is an agent published in the GitHub repository po4yka/RIPDPI (85 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 50 tokens to every session and 660 once invoked, about $0.0002 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.

Debugging Testing android android-vpn anti-censorship censorship-circumvention deep-packet-inspection dns-over-https

golden-blesser next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
golden-blesserpo4yka/RIPDPI	Agent	85	yesterday	BSD-3-Clause	A	50	Claude Code
reliability-engineervmobifystudio/app-dev-team	Agent	5	5d ago	MIT	A	62	Claude Code
patch-validatorParesh-Maheshwari/morphe-ai	Agent	194	1mo ago	GPL-3.0	A	36	Claude Code
target-hunterParesh-Maheshwari/morphe-ai	Agent	194	1mo ago	GPL-3.0	A	37	Claude Code
debug-experttienenwu/fables	Agent	4	3mo ago	MIT	A	226	Claude Code
crash-analyzerhyperb1iss/hyperdroid-skill	Agent	53	9mo ago	MIT	A	64	Claude Code
android-gradle-build-performancekrutikJain/android-agent-skills	Agent	14	7mo ago	MIT	A	27	Claude Code

RIPDPI: Agent for Claude Code