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 vrtalex/bitrix24-skill --skill bitrix24-agentgit clone --depth 1 https://github.com/vrtalex/bitrix24-skillWrote 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/vrtalex/bitrix24-skill/bitrix24-agent)<a href="https://agentmods.dev/skills/vrtalex/bitrix24-skill/bitrix24-agent"><img src="https://agentmods.dev/badge/skills/vrtalex/bitrix24-skill/bitrix24-agent/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/vrtalex/bitrix24-skill/bitrix24-agent"><img src="https://agentmods.dev/badge/skills/vrtalex/bitrix24-skill/bitrix24-agent.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 | $0.00214 | $0.02973 |
| Opus 5.5 | $0.00086 | $0.01189 |
| Sonnet 5.5 | $0.00043 | $0.00595 |
| Haiku 4.5 | $0.00021 | $0.00297 |
Grade A, and why
bitrix24-agent 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bitrix24 Agent (Lean + Reliable)
Use this skill to deliver correct Bitrix24 integrations with low token usage and production-safe defaults.
Quick Start
Use this flow unless the user asks for a different one:
- Pick intent + one minimal pack (
coreby default). - Run a read probe first.
- For writes, use plan then execute with confirmation.
Read probe:
python3 skills/bitrix24-agent/scripts/bitrix24_client.py user.current --params '{}'
Safer write flow:
python3 skills/bitrix24-agent/scripts/bitrix24_client.py crm.lead.add \
--params '{"fields":{"TITLE":"Plan demo"}}' \
--packs core \
--plan-only
python3 skills/bitrix24-agent/scripts/bitrix24_client.py \
--execute-plan <plan_id> \
--confirm-write
Runtime Prerequisites
Required environment:
B24_DOMAINB24_AUTH_MODE=webhookoroauth
Webhook mode:
B24_WEBHOOK_USER_IDB24_WEBHOOK_CODE
OAuth mode:
B24_ACCESS_TOKENB24_REFRESH_TOKENB24_CLIENT_IDandB24_CLIENT_SECRET(for--auto-refresh)
Useful safety/reliability flags:
B24_REQUIRE_PLAN=1for mandatory plan->execute on write/destructive callsB24_PACKS=core,...for default pack setB24_RATE_LIMITER=filewithB24_RATE_LIMITER_RATEandB24_RATE_LIMITER_BURST
Default Mode: Lean
Apply these limits unless the user asks for deep detail:
- Load at most 2 reference files before first actionable step.
- Start from
references/packs.md. - Then open only one target file:
references/catalog-<pack>.md. - Open
references/chains-<pack>.mdonly if the user needs workflow steps. - Open
references/bitrix24.mdonly for auth architecture, limits, event reliability, or unknown errors.
Response limits:
- Use concise output (goal + next action + one command).
- Do not retell documentation.
- Do not dump large JSON unless requested.
- Save your own tokens on reads: add
--out compact(minified) or--out summary(a{count, ids, next, total}digest for*.list); cap rows with--max-items N. Use the API'sselectin--paramsto fetch fewer fields. Default output is unchanged (full). - Return only delta if guidance was already given.
What ships with it
39 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.
- agents/openai.yaml 293 B
- references/bitrix24.md 27 KB
- references/catalog-automation.md 2.8 KB
- references/catalog-boards.md 2.3 KB
- references/catalog-booking.md 2.7 KB
- references/catalog-bots.md 3.0 KB
- references/catalog-collab.md 1.7 KB
- references/catalog-commerce.md 4.0 KB
- references/catalog-comms.md 5.0 KB
- references/catalog-compliance.md 954 B
- references/catalog-content.md 2.3 KB
- references/catalog-core.md 11 KB
- references/catalog-diagnostics.md 910 B
- references/catalog-mail.md 1.8 KB
- references/catalog-platform.md 1.8 KB
- references/catalog-services.md 2.3 KB
- references/catalog-sites.md 3.0 KB
- references/catalog-templates.md 1.5 KB
- references/chains-automation.md 494 B
- references/chains-boards.md 415 B
- references/chains-booking.md 319 B
- references/chains-bots.md 365 B
- references/chains-collab.md 397 B
- references/chains-commerce.md 1016 B
- references/chains-comms.md 439 B
- references/chains-compliance.md 279 B
- references/chains-content.md 1.1 KB
- references/chains-core.md 3.7 KB
- references/chains-diagnostics.md 620 B
- references/chains-mail.md 285 B
- references/chains-platform.md 358 B
- references/chains-services.md 356 B
- references/chains-sites.md 433 B
- references/chains-templates.md 295 B
- references/packs.md 3.8 KB
- scripts/bitrix24_client.py 60 KB runs code
- scripts/method_risk.json 8.1 KB
- scripts/offline_sync_worker.py 20 KB runs code
- scripts/required_params.json 7.7 KB
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 · 243 lines · 214 tokens per session scan A b5f6f59b45e2
bitrix24-agent is a skill published in the GitHub repository vrtalex/bitrix24-skill (26 stars, last pushed 4mo ago), licensed Unlicense. It adds 214 tokens to every session and 2,973 once invoked, about $0.0009 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 skills, from other repositories
bitrix
A specialist guide for 1C-Bitrix, a Russian content-management system and online-store platform. It examines the installed project, its standard modules, and local customisations before suggesting work.
om-system-extension
Extend installed Open Mercato modules through UMES enrichers, interceptors, mutation guards, widgets, menus, entity extensions, events, component/page replacements, and overrides. Use for "extend core", "add field/column/action", "hide page", "intercept API", "UMES", or "rozszerz moduł".
om-trim-unused-modules
Analyze and disable unused built-in modules in a standalone app without breaking dependencies, navigation, backend landing, bootstrap, or generation. Use for "trim classic mode", "remove unused modules", "slim app", "disable built-ins", or "wyłącz moduły".
agentsop-http-tool-wrapping
Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM agent can call. The load-bearing premise: the tool surface is an LM-friendly subset of the API surface — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling…
agentsop-streaming-output
Enhancement-overlay decision protocol for STREAMING the output of long-running LLM / agent runs from the backend, not just wiring a typing animation in the UI. Activates when a coder agent must stream final tokens to a chat client, surface intermediate agent steps (which tool, which node, partial reasoning), emit…
mcp-google-map-project
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.