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 agentmods add skills/rakovi4/continue-framework/qa-runnpx skills add rakovi4/continue-framework --skill qa-rungit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00080 | $0.01130 |
| Opus 5 | $0.00040 | $0.00565 |
| Sonnet 5 | $0.00016 | $0.00226 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
qa-run 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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qa-run - Run a Manual QA Checklist Against prod-copy
Drive the cases of a QA task (created by /task qa) against the live external
environment, one case at a time, in a headed browser the tester watches. Each
case either passes (tick the box) or fails (leave [ ], file a bug).
Executing the checklist also validates the checklist itself (the test model):
a case you cannot verify through the UI, or whose intent is ambiguous, is a defect
in the test model — fixed in the task spec.md — which is distinct from a product
defect, which becomes a /task bugfix.
Input
- target (optional): QA task number/slug. If absent, infer the in-progress QA task from the task progress files / recent git log.
Core Constraints
- UI-only navigation. Reach every page by clicking visible buttons, links, and
menu items — never type, paste, or script a direct in-app URL. The only allowed
direct-URL uses are the two carved out in
.claude/guidelines/frontend-rules.md("FORBIDDEN in-app navigation via URL"): the app root as the session entry point, and genuine external-arrival links a real user would click (an emailed verification or password-reset link). A manual tester must prove the same navigation paths a real user walks — the same constraint the Selenium rule applies to automated tests. - One action per step, watched. Connect to a headed browser the tester can see; perform a single action, then screenshot, then say what to look for. Never batch a whole case into one scripted run — the point is for the tester to watch each step.
- Real integrations, real creds. External-integration credentials (external-API
sandbox key, payment-gateway sandbox shop, mail inbox) come from
infrastructure/creds.txt(gitignored — NEVER commit) and from the tester as each case needs them. Never echo a secret into a committed file or a screenshot name. - Never block >30s (CLAUDE.md Interaction Rules). Long waits (a scheduler tick, email delivery) run in the background with short, separate polls (≤30s each).
- Read-only on infrastructure. prod-copy is a real environment — diagnose freely,
change nothing (see
.claude/rules/infrastructure.md). Read ports and base URLs from config; never hardcode them.
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.
- 3d ago First seen · 82 lines · 80 tokens per session scan A 065ac5673824
qa-run is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 80 tokens to every session and 1,130 once invoked, about $0.0004 per session on Opus 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 skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
e2e-deployment-skill
Use this deployment skill to verify shared skills load during Playwright startup.
launch
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
web-preview
Flutter Web版をビルド → サーバー起動 → Playwright でアクセス確認 → URLをユーザーに案内する。.