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 Mallikarjun-Roddannavar/playwright-agentic-automation --skill qa-safe-healinggit clone --depth 1 https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automationWrote 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/mallikarjun-roddannavar/playwright-agentic-automation/qa-safe-healing)<a href="https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/qa-safe-healing"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/qa-safe-healing/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/mallikarjun-roddannavar/playwright-agentic-automation/qa-safe-healing"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/qa-safe-healing.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 | $0.00029 | $0.01244 |
| Opus 5.5 | $0.00012 | $0.00498 |
| Sonnet 5.5 | $0.00006 | $0.00249 |
| Haiku 4.5 | $0.00003 | $0.00124 |
Grade A, and why
qa-safe-healing 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 19d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Safe Healing
Use this skill for failed tests, application incidents involving UI/API behavior,
diagnosis-only reports, and evidence-backed repair requests. Read applicable
AGENTS.md instructions before editing and use the UI/API owning skill for
implementation details.
Diagnose from evidence
- Use the failure policy below. Preserve original test output, traces/screenshots, network/API evidence, logs, source, and requirements. Keep generated summaries separate from original evidence.
- State the failing action, role, expected behavior, actual behavior, and test intent. Inspect exact named files first; use
rgand direct source reads as needed. No source index is required. - Follow the relevant path: UI action/state -> frontend request/session -> backend route/authorization -> persistence/configuration -> test assertion. Identify the responsible layer and compare with the closest working repository pattern.
- Separate facts, inferences, and pending runtime checks. Source inspection is not proof that a request ran. Name conflicting requirements or missing evidence; use
UNKNOWNwhen evidence cannot support classification. - Report classification, confidence, evidence locations, cause or supported hypothesis, modification decision, and remaining gaps. In diagnosis-only mode, change nothing. Do not claim final root cause while material evidence is missing.
Do not expose credentials, cookies, tokens, or private payloads. Use local dev/test for mutating reproduction. For production, use authorized read-only observation; data changes require explicit authorization and verification/rollback guidance.
Repair only when supported
APPLICATION_DEFECT, API_CONTRACT, ENVIRONMENT, and UNKNOWN preserve the
failing test. LOCATOR_DRIFT permits only a high-confidence locator-only repair.
TIMING, TEST_DATA, and ASSERTION_ERROR require human review under the policy below.
When the user authorizes an application fix, repair the proven application layer and preserve the regression expectation. A product defect is not permission to heal its failing test.
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.
- 19d ago Changed · +97 lines · +6 tokens per session 95452871729c
- 1mo ago First seen · 18 lines · 23 tokens per session scan A 322f587b599b
qa-safe-healing is a skill published in the GitHub repository Mallikarjun-Roddannavar/playwright-agentic-automation (13 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 1,244 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 2026-09-08.
Other skills, from other repositories
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
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.…
prevent-recurrence
Use when correcting an issue or failure reveals a reusable prevention lesson, including code, setup, measurement, validation, workflow, agent mistakes, or accepted code-review findings; when someone says "this keeps happening" or asks how to stop it; or in post-incident follow-up. Fixes the instance (failing-first…
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
qa-expert
Expert-level quality assurance, testing strategies, automation, and QA processes. Use when the user mentions testing, test automation, quality assurance, or Selenium, or when the task involves Testing Types, QA Processes, Test Strategy, or Defect Management.
investigate
A structured root-cause investigation method for software bugs. It moves from history and reproduction through tested hypotheses, a focused fix, verification, and a report.