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.
curl -O https://raw.githubusercontent.com/Matthew-M-King/robot-framework-mcp-server/main/.claude/commands/rf-triage.mdgit clone --depth 1 https://github.com/Matthew-M-King/robot-framework-mcp-serverWrote 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.
[](https://agentmods.dev/commands/matthew-m-king/robot-framework-mcp-server/rf-triage)<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>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 | $0.00000 | $0.01132 |
| Opus 5 | $0.00000 | $0.00566 |
| Sonnet 5 | $0.00000 | $0.00226 |
| Haiku 4.5 | $0.00000 | $0.00113 |
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.
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 arobot/output.xmlinside)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: trueis 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_countandareas_affectedfailure_type(functional/infra-keyword/infra-setup/setup-other)failure_pattern(normalised root-cause fingerprint)representative_testandxml_pathinvestigation_hintsescalated(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.
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.
- 7d ago First seen · 131 lines · 0 tokens per session scan A fde2245240cc
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.
Other commands, from other repositories
ui-aqa-flow-test-report-analysis
Phase 7 Test Report Analysis of ui-aqa-flow.
api-aqa-flow-execution-and-report-analysis
Phase 6 Execution & Report Analysis of api-aqa-flow (USER INTERACTION REQUIRED).
ui-aqa-flow-code-analysis
Phase 3 Code Analysis of ui-aqa-flow.
verify-pr
Verify a PR's frontend changes through browser automation.
eval
Legacy slash-entry shim for the eval-harness skill. Prefer the skill directly.
multi-page
Smoke test multiple pages in parallel using alethiatellparallel.