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 bitrix24/templates-mcp --skill run-manual-qagit clone --depth 1 https://github.com/bitrix24/templates-mcpWrote 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/bitrix24/templates-mcp/run-manual-qa)<a href="https://agentmods.dev/skills/bitrix24/templates-mcp/run-manual-qa"><img src="https://agentmods.dev/badge/skills/bitrix24/templates-mcp/run-manual-qa/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/bitrix24/templates-mcp/run-manual-qa"><img src="https://agentmods.dev/badge/skills/bitrix24/templates-mcp/run-manual-qa.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 | $0.00052 | $0.02995 |
| Opus 5.5 | $0.00021 | $0.01198 |
| Sonnet 5.5 | $0.00010 | $0.00599 |
| Haiku 4.5 | $0.00005 | $0.00299 |
Grade A, and why
run-manual-qa 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
run-manual-qa — Agent Skill
Manual QA for the Bitrix24 MCP server. The server is exercised twice per run: once through the MCP Inspector (deterministic, parameter-level) and once through an AI agent connector (natural-language disambiguation). This skill produces a single tracking issue the human clicks through, and archives the result so the next run starts from known state.
Hard rules
- Never write test artifacts into
bitrix24/templates-mcp. Tracking issues, fail reports, and result archives go into a separate disposable test repo (e.g.IgorShevchik/for-test-mcp). The upstream repo only ever receives the skill itself and real PRs — never QA scratch. - Never ask for, store, echo, or commit secrets. The human supplies every secret (webhook URL, MCP auth token, GitHub PAT) directly into their local
.env. The skill describes which variables are needed and where they come from — it never handles the values. If a value looks like a real token in any input, refuse to write it anywhere. - Always ask the three run parameters before doing anything (see Step 0). Do not assume scope, repo, or language from a previous session.
- Test phrases render in the human's chosen language; everything structural is English. The project's documentation language is English (section titles, labels, archive). Only the operator-facing test phrases (the "say this to the AI agent" lines) use the chosen language.
- Keep the scaffold in sync with the project.
references/issue-scaffold.mdhard-codes structural facts. Update it in the same PR whenever the underlying fact changes — not merely when a file is touched. Triggers (by change, not by filename): aNUXT_*/NITRO_*variable added/renamed/removed; the default port or/mcpendpoint path changed; a required webhook scope changed; the connector auth header name/format changed; a new tool that needs upfront-seeded portal data. (Anuxt.config.tsrefactor that changes none of these needs no scaffold edit.) The data table and seed list are otherwise generated/trimmed per run. A CI gate enforces the.env.example↔ scaffold pairing — see.github/workflows/.
What ships with it
2 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.
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.
- 1mo ago First seen · 122 lines · 52 tokens per session scan A d7948ea76bbd
run-manual-qa is a skill published in the GitHub repository bitrix24/templates-mcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,995 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 2026-08-31.
Other skills, from other repositories
field-test
Exercise tools, resources, and prompts against a live HTTP server via MCP JSON-RPC over curl. Starts the server, surfaces the catalog, runs real and adversarial inputs, measures every call (bytes, token estimate, wall-clock) and weighs the catalog, renders app tools' views in a headless MCP Apps host, and produces a…
ux-acceptance-coordinator
Coordinate black-box, agent-driven UX acceptance journeys against a disposable EmDash admin site. Use when preparing, dispatching, verifying, or reporting a manual browser journey performed by a separate tester agent. Do not use for deterministic Playwright tests or ordinary code review.
ux-acceptance-tester
Perform a goal-driven, black-box UX acceptance journey in a browser and report the path, friction, and observable outcome. Use only in an isolated tester context with a supplied start URL and brief.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
integration-e2e-testing
Selects and designs the smallest integration/E2E test set that proves accepted behavior at an observable boundary. Use when writing or reviewing E2E or integration tests.
release-parity-test
Use before cutting a release, after a change to live reads, write tools or skills, or when the user asks to test the MCP against the web app. Runs the three-way parity test in test-matrix.md (cache mode vs live MCP vs app.copilot.money), including round-trip writes with throwaway test data in the user's Manual…