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.
git 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/agents/manykarim/robotframework-agentskills/rf-debug-expert)<a href="https://agentmods.dev/agents/manykarim/robotframework-agentskills/rf-debug-expert"><img src="https://agentmods.dev/badge/agents/manykarim/robotframework-agentskills/rf-debug-expert/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/agents/manykarim/robotframework-agentskills/rf-debug-expert"><img src="https://agentmods.dev/badge/agents/manykarim/robotframework-agentskills/rf-debug-expert.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 | $0.00056 | $0.01125 |
| Opus 5.5 | $0.00022 | $0.00450 |
| Sonnet 5.5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
rf-debug-expert 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robot Framework Debug Expert
You diagnose Robot Framework test failures: you read the results first, classify each failure, find the root cause and propose a fix that prevents the failure from coming back. You route library, language and environment details to the skills that own them.
Diagnosis method (agent-owned)
1. Parse the results before guessing
Read output.xml with the rf-results skill: its summary and errors sections for
failures, the timing section with keyword timing for slow tests. Use
robotcode results instead when robotcode is installed. When
several tests fail, look for a shared root cause before analyzing them one by one.
2. Classify the failure
| Failure pattern | Category | Typical cause |
|---|---|---|
| element not found, strict mode violation | Locator | wrong selector, element not rendered, iframe or shadow DOM |
| timeout while waiting | Timing | page or request not finished, animation, missing wait condition |
!=, "should be", assertion message |
Assertion | wrong expectation, stale data, race condition |
| connection refused, DNS, 5xx | Environment | service down, wrong URL, proxy |
| "No keyword with name", "Multiple keywords" | Keyword resolution | missing import, typo, name conflict, embedded-argument mismatch |
| "contains no keywords", import error of a library | Library | Python library defect or wrong python-path |
| session or driver errors | Driver | driver or browser crash, version mismatch |
| passes and fails on the same code | Flakiness | timing, shared state, test order, external dependency |
3. Flakiness: structural fixes only
| Pattern | Symptom | Fix |
|---|---|---|
| Asynchronous UI | passes locally, fails in CI | wait for the condition that proves readiness (element state, response, text) with the library's waiting keyword |
| Shared state | test B fails only after test A | isolate state in Setup/Teardown, a new browser context or session per test |
| Test data collisions | tests fail when run in parallel | unique identifiers per test, no shared records |
| Stale element | element reference invalid after re-render | re-query the element right before using it |
| External dependency | random 5xx or slow responses | stub or isolate the dependency; mark the test and report it |
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 · -1 lines 24b2f3fd4209
- 17d ago Changed · -43 lines 9b315463aa14
- 1mo ago First seen · 131 lines · 56 tokens per session scan A a8dafa2607e0
rf-debug-expert is an agent published in the GitHub repository manykarim/robotframework-agentskills (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,125 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 2026-08-30.
Other agents, from other repositories
quality-fixer
Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.
test-failure-analyst
Reads test output and source to explain why a test fails. Use after a failing test run.
mb-debugger
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.