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.
npx skills add manykarim/robotframework-agentskills --skill rf-robotcodegit clone --depth 1 https://github.com/manykarim/robotframework-agentskillsWrote 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/skills/manykarim/robotframework-agentskills/rf-robotcode)<a href="https://agentmods.dev/skills/manykarim/robotframework-agentskills/rf-robotcode"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/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.
<a href="https://agentmods.dev/skills/manykarim/robotframework-agentskills/rf-robotcode"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/rf-robotcode.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00030 | $0.02392 |
| Opus 5.5 | $0.00012 | $0.00957 |
| Sonnet 5.5 | $0.00006 | $0.00478 |
| Haiku 4.5 | $0.00003 | $0.00239 |
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 11d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
robotcode CLI Skill
When to use
Load this skill first, before reading robot.toml or exploring the tests, when a Robot Framework project uses the robotcode CLI or a robot.toml:
- run suites with robot.toml profiles, discover tests and tags without running them;
- debug a failing test step by step with robot-debug, or try keywords in a non-interactive REPL;
- keyword docs (
robotcode libdoc), result summaries, failures and diffs of output.xml (robotcode results), static checks (robotcode analyze code).
Not this skill: settings of the RobotCode VS Code extension. Without robotcode, use rf-results for output.xml and rf-libdoc for keyword docs.
Quick Reference
robotcode is the CLI of the RobotCode project (the same engine as the VS Code extension). It wraps robot, libdoc, rebot and testdoc with the project's robot.toml configuration, and adds discovery, a REPL, a CLI debugger, result analysis and static analysis. Every command reads the same robot.toml and profiles.
Verified against robotcode 2.7.0, Robot Framework 7.5.
Is robotcode available?
Check once per session, from the project root:
robotcode --version # or, in a uv project: uv run robotcode --version
robotcode discover info # which Python / RF / robotcode will actually be used
- Available → use the commands below.
- Not installed → use the script-based skills instead (see Companion Skills), or, if the user agrees, install it into the project environment:
uv add --dev "robotcode[all]"(orpip install "robotcode[all]"in the active venv). - Run robotcode from the project's environment (
uv run robotcode …or the activated venv). A global install sees the wrong library versions.
⚠️ Agent safety rule: never run the REPL or debugger interactively
robotcode repl and robotcode robot-debug are interactive. In scripts and agent terminals:
- Pipe the input in (
printf '…' | robotcode replorrobotcode repl < steps.robotrepl), or pass--plain. - End piped REPL input with
.exit. - In a real terminal (PTY) without agent detection, piped lines become one pasted block and the REPL hangs. robotcode detects agent terminals (
CLAUDECODE,AI_AGENT, …) and switches to the plain backend.ROBOTCODE_FORCE_AI_AGENT=1forces this on. Seereferences/agent-mode.md. - If stdin ends (EOF) while the debugger is paused, the run resumes and finishes. It does not hang.
What ships with it
15 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.
- assets/examples/debug_target.robot 614 B
- assets/examples/debug-at-failure.rdb 146 B
- assets/examples/explore-api.robotrepl 845 B
- assets/examples/explore-browser.robotrepl 1.0 KB
- assets/examples/robot.toml 929 B
- references/agent-mode.md 2.8 KB
- references/analyze.md 5.0 KB
- references/debug.md 7.3 KB
- references/discover.md 2.9 KB
- references/gotchas.md 4.5 KB
- references/libdoc.md 3.2 KB
- references/repl.md 5.5 KB
- references/results.md 4.5 KB
- references/run-and-wrapper.md 2.7 KB
- references/setup-and-config.md 4.2 KB
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.
- 11d ago Changed · -4 tokens per session 71d607780d41
- 17d ago First seen · 143 lines · 34 tokens per session scan A 2031852c8d68
rf-robotcode is a skill published in the GitHub repository manykarim/robotframework-agentskills (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 30 tokens to every session and 2,392 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.