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 bxmaximum/bitrix-framework-skills --skill bitrix24-ai-toolsgit clone --depth 1 https://github.com/bxmaximum/bitrix-framework-skillsWrote 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/bxmaximum/bitrix-framework-skills/bitrix24-ai-tools)<a href="https://agentmods.dev/skills/bxmaximum/bitrix-framework-skills/bitrix24-ai-tools"><img src="https://agentmods.dev/badge/skills/bxmaximum/bitrix-framework-skills/bitrix24-ai-tools/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/bxmaximum/bitrix-framework-skills/bitrix24-ai-tools"><img src="https://agentmods.dev/badge/skills/bxmaximum/bitrix-framework-skills/bitrix24-ai-tools.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 | $0.00070 | $0.01517 |
| Opus 5.5 | $0.00028 | $0.00607 |
| Sonnet 5.5 | $0.00014 | $0.00303 |
| Haiku 4.5 | $0.00007 | $0.00152 |
Grade A, and why
bitrix24-ai-tools 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 16d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bitrix24 AI tools
Baseline: Bitrix24 cloud; on-premise via vibecodeconnector · Verified: b24restdocs 2026-09-30, vibecodeconnector 26.200.100 (main 26.800.0)
| Goal | Use |
|---|---|
| Write or change REST calls in your own code | MCP b24-dev-mcp + bitrix24-rest-api |
| Have an agent build and host an app on the platform | Alaio Vibecode |
| Agent-ready starters | b24gosdk llms.txt; github.com/bitrix24/b24-ai-starter (Nuxt 3 + PHP/Python/Node, OAuth, Docker) |
No llms.txt is documented for the REST docs themselves. Vibecode (platform) ≠ Vibe (start page, landing.repowidget.*) ≠ Vibe+ (cloud plan line).
Docs MCP b24-dev-mcp
https://mcp-dev.bitrix24.com/mcp: Streamable HTTP (no /sse), no auth. It serves docs only: no portal data, no method calls. The client must accept application/json and text/event-stream (otherwise 406).
| Tool | Call when |
|---|---|
bitrix-search |
first; returns exact names. doc_type: method, event, other, app_development_docs; limit |
bitrix-method-details |
before writing a call: params, required fields, response, errors, samples (field, filter narrow it) |
bitrix-event-details |
writing an event handler: payload |
bitrix-article-details |
concepts: auth, limits, batch, pagination |
bitrix-app-development-doc-details |
app install, placements, app types |
Setup:
claude mcp add --transport http b24-dev-mcp https://mcp-dev.bitrix24.com/mcp
codex mcp add b24-dev-mcp --url https://mcp-dev.bitrix24.com/mcp
Cursor .cursor/mcp.json: {"mcpServers": {"b24-dev-mcp": {"url": "https://mcp-dev.bitrix24.com/mcp", "timeout": 30000}}}. VS Code .vscode/mcp.json: {"servers": {"b24-dev-mcp": {"url": "https://mcp-dev.bitrix24.com/mcp", "type": "http"}}}. Smoke test: ask for crm.item.add params; the answer must name entityTypeId and fields.
Rules:
- Before adding or changing a REST call:
bitrix-search, thenbitrix-method-detailson the exact name. Take param names and case, required fields, filter syntax and scope from the result, not from memory. not foundmeans an inexact name: search again, never guess.- The docs describe the cloud. Whether a method exists on a given box:
method.geton that portal. - Never send webhook URLs, tokens, keys or customer data to the MCP.
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.
- 16d ago First seen · 81 lines · 70 tokens per session scan A 463189247338
bitrix24-ai-tools is a skill published in the GitHub repository bxmaximum/bitrix-framework-skills (45 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 1,517 once invoked, about $0.0003 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
prompt-engineer-toolkit
Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics. Use when designing production prompts, running A/B tests, or building prompt libraries.
llm-cost-optimizer
This skill should be used when the user asks to "estimate LLM costs", "count tokens in prompts", "optimize prompt token usage", "compare model pricing", or "reduce LLM API costs".
prompt-governance
This skill should be used when the user asks to "audit prompts for safety", "check prompts for injection vulnerabilities", "manage a prompt catalog", "version control prompts", or "review prompt quality and compliance".
dspy-gepa
Optimize instructions in DSPy programs via reflective evolution using dspy.GEPA without adding few-shot examples. Use when you want to optimize instructions without few-shot examples — a lightweight alternative when you do not have or do not want to use demonstrations. Common scenarios - optimizing instructions when…
ai-following-rules
Make your AI follow rules and policies. Use when your AI breaks format rules, violates content policies, ignores business constraints, outputs invalid JSON, exceeds length limits, includes forbidden content, or does not comply with your specifications. Also use when LLM JSON output is unreliable, you get inconsistent…
dspy-better-together
Jointly optimize prompts and model weights using dspy.BetterTogether for maximum accuracy. Use when you have already tried prompt-only optimization and want the next level — jointly tuning prompts and model weights for maximum quality. Common scenarios - you have maxed out prompt optimization and need the next level…