What is rf-robotcode?

A guide and tool workflow for Robot Framework, a system for writing automated tests in readable keyword-style files. It uses rf-mcp tools to discover, write, run, inspect, and debug tests.

Use it to author Robot Framework tests, discover suites and profiles, analyze files, run tests, inspect results, and debug failures.

It gives each testing task a defined tool and order, so you can find the right suites, investigate failures, and inspect live tests without relying on shell commands or copied output.

rf-robotcode — Skill for Claude Code and Codex by manykarim/rf-mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add manykarim/rf-mcp --skill rf-robotcode

Clone the repo

git clone --depth 1 https://github.com/manykarim/rf-mcp

Made for: Claude Code, Codex.

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/skills/manykarim/rf-mcp/rf-robotcode/github.svg)](https://agentmods.dev/skills/manykarim/rf-mcp/rf-robotcode)

Your own site

<a href="https://agentmods.dev/skills/manykarim/rf-mcp/rf-robotcode"><img src="https://agentmods.dev/badge/skills/manykarim/rf-mcp/rf-robotcode/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/skills/manykarim/rf-mcp/rf-robotcode"><img src="https://agentmods.dev/badge/skills/manykarim/rf-mcp/rf-robotcode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 897 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	$0.00051	$0.00897
Opus 5.5	$0.00020	$0.00359
Sonnet 5.5	$0.00010	$0.00179
Haiku 4.5	$0.00005	$0.00090

Measured 2d ago against content hash 782966632d68, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rf-robotcode 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 2d 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.

src/robotmcp/skills/builtin/rf-robotcode/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Robot Framework with rf-mcp

The rf_* tools run robotcode in the project's environment. Use them instead of shell commands, file greps or reading output.xml.

Pick the mode first

Intent	Tool	Details
What tests, tags, suites, files, profiles exist?	`rf_discover`	large-projects
Why did X fail? Fix this test.	`rf_results` first, then `rf_debug`	triage
A real test is involved and must be inspected live	`rf_debug` - never a REPL copy	debugging
Explore a library, page or API; write a new test	`rf_repl`	repl-authoring
Check files without running	`rf_analyze`	analyze
Keyword names, arguments, docs	`rf_doc`, `.kw`, `.doc`	repl-authoring
Run tests and report	`rf_run`, then `rf_results`	results
Profiles, robot.toml, environment	`rf_discover action=profile_show`	config-profiles

Several modes chain: explore, then author, then run, then inspect.

Rules that save the most turns

Longnames, not files. Select with by_longname taken from rf_discover. A single .robot file in paths becomes the top suite: parent __init__.robot setups are skipped and longnames lose their prefix.
Recorded run first. For "why did X fail?" call rf_results (action="show", failed_only=true, then action="log", by_longname=[...]) before reading files or debugging. Never read or grep output.xml.
Debugger for real tests. If an existing test is involved, rf_debug it; a REPL copy runs a misleading imitation.
Analyze before running. rf_analyze after every edit; fix KeywordNotFound and argument errors before rf_run.
Look keywords up. rf_doc action=keywords (several name patterns at once) or .kw <text> in the REPL; never guess names or argument order.
One session, reused. Start one rf_repl session, send several known steps per send, and stop it at the end (or say it is still open).
Every test stands alone. Each test creates its own data and passes when run alone by longname.
Done means verified. A task is done only when rf_analyze is clean and rf_run passes.

Read the full file on GitHub · 46 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

2d ago First seen · 46 lines · 51 tokens per session scan A 782966632d68

Subscribe to this mod's changes

rf-robotcode is a skill published in the GitHub repository manykarim/rf-mcp (118 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 897 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 2026-11-12.

Python Testing ai automation mcp robotframework

rf-robotcode next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rf-robotcodemanykarim/rf-mcp	Skill	118	yesterday	Apache-2.0	A	51	Claude Code, Codex
schema-explorationlangchain-ai/deepagents	Skill	31k	today	MIT	A	57	Claude Code, Codex
mempalace-recallMemPalace/mempalace	Skill	61k	yesterday	MIT	A	94	Claude Code
matlabK-Dense-AI/scientific-agent-skills	Skill	57k	5d ago	MIT	A	44	Claude Code
mem0-oss-to-platformmem0ai/mem0	Skill	69k	8d ago	Apache-2.0	A	217	Claude Code, Codex
analyze-marketlangchain-ai/deepagents	Skill	31k	today	MIT	A	34	Claude Code, Codex
haikuagno-agi/agno	Skill	43k	today	Apache-2.0	A	0	Claude Code, Codex