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 instructions/bitrix24/b24ui/agents-mdgit clone --depth 1 https://github.com/bitrix24/b24uiWhat 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 | $0.02892 | $0.02892 |
| Opus 5 | $0.01446 | $0.01446 |
| Sonnet 5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
b24ui AGENTS.md 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 2d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance for AI coding agents working on the Bitrix24 UI repository.
Project Overview
Bitrix24 UI is a component library built on Reka UI, Tailwind CSS, and Tailwind Variants. It provides accessible, themeable components for both Nuxt and Vue applications.
Project Structure
src/
├── runtime/
│ ├── components/ # Vue components (PascalCase.vue)
│ ├── composables/ # Composables (use*.ts)
│ ├── types/ # TypeScript types
│ └── utils/ # Utility functions
├── theme/ # Tailwind Variants themes (kebab-case.ts)
└── module.ts
test/
├── components/ # Component tests (*.spec.ts)
│ └── __snapshots__/ # Auto-generated snapshots
└── component-render.ts
docs/
└── content/docs/2.components/ # Documentation (*.md)
playgrounds/
└── nuxt/app/pages/components/ # Playground pages
Commands
pnpm run dev:prepare # Generate type stubs (run after install)
pnpm run dev # Nuxt playground
pnpm run dev:vue # Vue playground
pnpm run repl # REPL playground
pnpm run demo # Demo playground
pnpm run docs # Documentation site
pnpm run lint # Check linting
pnpm run lint:fix # Fix linting
pnpm run typecheck # Type checking
pnpm run test # Run tests
pnpm run skill:sync # Regenerate skills/index.json from the skill tree
CLI for Scaffolding
Link the CLI first (one-time setup):
npm link
Then use it to create new components:
bitrix24-ui make component <name> [options]
Options:
--primitive- Primitive component (uses Reka UI Primitive)--prose- Prose/typography component--content- Content component--template- Generate specific template only (playground,docs,test,theme,component)
Key Conventions
- Conventional commits: All commit messages must follow conventional commits, and the type must have a section in
changelog-sections(release-please-config.json) — one that does not is dropped from the changelog, or, if the commit is breaking, rendered under a raw lowercase heading above every real section.assert-commit-parses.mjsrejects it, and rejects a port whose subject does not name the upstream commit as(nuxt/ui@<sha>)(e.g.fix(Button): resolve hover state,feat(Modal): add fullscreen prop). A revert must be titledrevert(Scope): …— GitHub's revert button producesRevert "…", which release-please rejects outright, so the revert reaches no changelog and, if it is the only commit since the last tag, opens no release PR at all. - Releases are automated: merging work into
mainpublishes nothing; release-please keeps one release PR open and merging that tags, releases and publishes to npm. Version arithmetic (feat/feature-> minor,fix-> patch), the release cadence commitment, theseverity:crashhotfix policy, therevert:subject a revert PR must carry, and the manual CI approval the release PR needs before it can merge all live in releasing.md. Filed here rather than in the References table below, which is scoped tosrc/andtest/work. - Semantic colors: Use
text-description,bg-elevated, etc. — never raw Tailwind palette colors liketext-gray-500. - Dependency pins are not ours to move:
reka-uiandvaul-vueare exact-pinned inpackage.jsonbecause upstream pins them at those exact versions; they change through a port, never through a local bump. Andvueis declared as a required peer (^3.5.0) even though upstream does not declare it —src/usesuseTemplateRefanduseId, both Vue 3.5. Both facts are invariants in .sync/PORTING.md §2 and guarded bytest/utils/peer-dependencies.spec.ts. Soonbadge on docs headings: PRs that introduce a new feature or fix often add:badge{label="Soon" class="align-text-top"}to the relevant docs heading. This is intentional: the docs site redeploys on merge, but the feature only ships on the next npm release — the badge bridges that gap. Do NOT flag this as inconsistent in reviews. See documentation.md for details.- Skill files live in
skills/: Whenever a request mentions editing, adding, or refining a skill (SKILL.md, references, recipes, guidelines, layouts), modify the tracked tree underskills/<skill-name>/— NOT under.claude/skills/(which is gitignored and local-only). The exception is when the user explicitly names the.claude/skills/path. If both copies exist, treatskills/as the source of truth and ignore.claude/skills/.skills/index.jsonis generated — after adding, removing or renaming a file there, runpnpm run skill:syncrather than editing it by hand;test/utils/skill-manifest.spec.tsfails if the committed file is stale, becausenpx skills addinstalls exactly what it lists and an unlisted file is silently never delivered.
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.
- 2d ago First seen · 161 lines · 2,892 tokens per session scan A e000a311f8dd
b24ui AGENTS.md is an instructions file published in the GitHub repository bitrix24/b24ui (41 stars, last pushed 2d ago), licensed MIT. It adds 2,892 tokens to every session, about $0.0145 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.