a2a-tck: Skill for Claude Code

.agents/skills/diagnose-failure/SKILL.md

diagnose-failure is a skill for Claude Code from a2aproject/a2a-tck. It costs 60 tokens per session (2,145 once invoked), scanned B, original, Apache-2.0.

A guide for investigating an A2A TCK failure and drafting a GitHub issue for the developer of the tested agent. It uses the failed requirement, recorded test details, and a curl command that reproduces the problem.

In plain words
What is it for?
Use it to diagnose failed requirements, collect evidence from compatibility reports, and prepare an issue with protocol context and reproduction steps.
Why use it?
It turns a vague test failure into a specific, actionable bug report. It also helps group related failures that may have the same underlying cause.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is a2aproject/a2a-tck's own configuration. It tells Claude Code how to work on a2a-tck itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything a2a-tck configures →

Reuse

Borrowing it

Nothing to install: this file belongs to a2aproject/a2a-tck. 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/a2aproject/a2a-tck/main/.agents/skills/diagnose-failure/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/a2aproject/a2a-tck

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 diagnose-failure

README.md
[![agentmods](https://agentmods.dev/badge/skills/a2aproject/a2a-tck/diagnose-failure/github.svg)](https://agentmods.dev/skills/a2aproject/a2a-tck/diagnose-failure)
Your own site
<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/diagnose-failure"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/diagnose-failure/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 diagnose-failure

Your own site · 80×15
<a href="https://agentmods.dev/skills/a2aproject/a2a-tck/diagnose-failure"><img src="https://agentmods.dev/badge/skills/a2aproject/a2a-tck/diagnose-failure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,145 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 3
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Data Exfiltration · line 107
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 5.1 $0.00060 $0.02145
Opus 5 $0.00030 $0.01073
Sonnet 5 $0.00012 $0.00429
Haiku 4.5 $0.00006 $0.00215

Measured 9d ago against content hash 37c7ee83f813, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

diagnose-failure scanned grade B with 2 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.

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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

grpcurl -plaintext -d '<JSON>' <GRPC_HOST>:<PORT> <PACKAGE>.<SERVICE>/<RPC>

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: Diagnose a TCK requirement failure and draft a GitHub issue with the requirement context, failure details, and a curl reproducer. Use when the user wants to report a failing requirement, understand why it fa
.agents/skills/diagnose-failure/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diagnose a TCK Failure and Draft a GitHub Issue

Follow these steps to diagnose a failing requirement and produce a GitHub issue body that an SUT implementor can act on.

Step 1: Identify the failing requirement

Ask the user for one of:

  • A requirement ID (e.g., PUSH-CREATE-001, GRPC-ERR-001)
  • A test name from the TCK output
  • A transport + error description

Read reports/compatibility.json to find the failing requirement, its status per transport, recorded errors, and test_ids. This file is always generated after every TCK run. The structure uses per_requirement (a dict keyed by requirement ID), not a list. Example: data["per_requirement"]["VER-SERVER-002"].

Multi-requirement grouping: When scanning the report, look for related requirements that likely share the same root cause (e.g., same test module, similar error messages, same spec section). Group them early so all context is gathered together rather than diagnosed separately.

Use the SUT URL from the current session or from reports/compatibility.json (summary.sut_url) rather than asking the user again.

Step 2: Gather requirement context

Look up the RequirementSpec in the appropriate file under tck/requirements/:

tck/requirements/core_operations.py    — CORE-*
tck/requirements/binding_grpc.py       — GRPC-*
tck/requirements/binding_jsonrpc.py    — JSONRPC-*
tck/requirements/binding_http_json.py  — HTTP_JSON-*
tck/requirements/data_model.py         — data model requirements
tck/requirements/streaming.py          — streaming requirements
tck/requirements/push_notifications.py — push notification requirements
tck/requirements/agent_card.py         — agent card requirements
tck/requirements/auth.py               — authentication requirements
tck/requirements/versioning.py         — versioning requirements
tck/requirements/interop.py            — interoperability requirements

Extract:

  • ID, section, title, level, description
  • Transport binding — the HTTP method + path, JSON-RPC method, and gRPC RPC name
  • Expected behavior
  • spec_url — convert to a GitHub link (see below)

Read the full file on GitHub · 215 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. 9d ago First seen · 215 lines · 60 tokens per session scan B 37c7ee83f813

Subscribe to this mod's changes

diagnose-failure is a skill published in the GitHub repository a2aproject/a2a-tck (49 stars, last pushed 7d ago), licensed Apache-2.0. It adds 60 tokens to every session and 2,145 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens