robot-framework-mcp-server: Command for Claude Code

.claude/commands/rf-triage.md

rf-triage is a command for Claude Code from Matthew-M-King/robot-framework-mcp-server. It costs 0 tokens per session (1,132 once invoked), scanned A, original, MIT.

A command for analysing Robot Framework test results, where Robot Framework is a tool for automated acceptance and system tests. It uses a local analysis server to build a failure matrix and prioritised investigation plan.

In plain words
What is it for?
Use it with a directory containing Robot Framework output files to ingest results, generate an HTML failure matrix and plan which failures to investigate first.
Why use it?
It turns result folders into an organised view of failures, reducing the need to inspect every failed test manually. An optional area filter narrows the analysis to one part of the system.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is Matthew-M-King/robot-framework-mcp-server's own configuration. It tells Claude Code how to work on robot-framework-mcp-server 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 robot-framework-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Matthew-M-King/robot-framework-mcp-server. 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/Matthew-M-King/robot-framework-mcp-server/main/.claude/commands/rf-triage.md
Clone the repo
git clone --depth 1 https://github.com/Matthew-M-King/robot-framework-mcp-server

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 rf-triage

README.md
[![agentmods](https://agentmods.dev/badge/commands/matthew-m-king/robot-framework-mcp-server/rf-triage.svg)](https://agentmods.dev/commands/matthew-m-king/robot-framework-mcp-server/rf-triage)
Your own site
<a href="https://agentmods.dev/commands/matthew-m-king/robot-framework-mcp-server/rf-triage"><img src="https://agentmods.dev/badge/commands/matthew-m-king/robot-framework-mcp-server/rf-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,132 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01132
Opus 5 $0.00000 $0.00566
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 7d ago against content hash fde2245240cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

rf-triage 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 7d 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.

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/commands/rf-triage.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robot Framework Failure Triage

Analyse Robot Framework test results using the rf-test-analysis-mcp server and produce a prioritised investigation plan. Works with any Robot Framework test suite — no product-specific knowledge required.

Prerequisites

The FastAPI HTTP server must be running:

python -m uvicorn robot_mcp_server.http_server:app --host 127.0.0.1 --port 8000

Usage

/rf-triage <results_dir> [area_filter]
  • results_dir — path to the directory that contains your Robot Framework result folders (each folder should have a robot/output.xml inside)
  • area_filter — optional substring to restrict analysis to one area (e.g. Checkout)

Workflow

Follow these steps in order. Use the MCP tools exposed by the running server.

Step 1 — Ingest

Call ingest_results(results_dir=<results_dir>).

  • If already_current: true is returned, the data is already up to date — skip to Step 3.
  • On a fresh run this may take a few minutes; wait for the response before continuing.

Step 2 — Generate failure matrix

Call generate_failure_matrix(results_dir=<results_dir>, output_format="html").

Report the path of the generated HTML file to the user so they can open it in a browser.

Step 3 — Get triage queue

Call get_triage_queue(results_dir=<results_dir>, area_filter=<area_filter>, top_n=20).

For each item in the queue, note:

  • rank, score, priority_label (P1–P4)
  • failure_count and areas_affected
  • failure_type (functional / infra-keyword / infra-setup / setup-other)
  • failure_pattern (normalised root-cause fingerprint)
  • representative_test and xml_path
  • investigation_hints
  • escalated (true = API response-code failure, treat as P1 regardless of label)

Step 4 — Expand high-priority groups

For each group with score >= 55 (P1 or P2):

Call get_group_tests(results_dir=<results_dir>, failure_pattern=<failure_pattern>).

List all affected test names and areas so the user sees the full blast radius.

Read the full file on GitHub · 131 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. 7d ago First seen · 131 lines · 0 tokens per session scan A fde2245240cc

Subscribe to this mod's changes

rf-triage is a command published in the GitHub repository Matthew-M-King/robot-framework-mcp-server (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,132 tokens. 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 2026-08-31.