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/caipe-io/ai-platform-engineering/agents-mdgit clone --depth 1 https://github.com/caipe-io/ai-platform-engineeringWrote 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/instructions/caipe-io/ai-platform-engineering/agents-md)<a href="https://agentmods.dev/instructions/caipe-io/ai-platform-engineering/agents-md"><img src="https://agentmods.dev/badge/instructions/caipe-io/ai-platform-engineering/agents-md.svg" alt="Measured on agentmods" 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 | $0.01712 | $0.01712 |
| Opus 5 | $0.00856 | $0.00856 |
| Sonnet 5 | $0.00342 | $0.00342 |
| Haiku 4.5 | $0.00171 | $0.00171 |
Grade A, and why
ai-platform-engineering 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 5d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Structure
ai_platform_engineering/ # Python backend
mcp/ # Per-tool MCP servers (GitHub, ArgoCD, etc.)
dynamic_agents/ # Dynamic agents runtime (FastAPI, MongoDB, AG-UI/SSE)
integrations/ # Slack and Webex bot integrations
autonomous_agents/ # Scheduled and event-driven autonomous tasks
audit_service/ # Audit-event service
scheduler/ # Scheduler service
cron-runner/ # Cron job runner
knowledge_bases/rag/ # RAG server, ingestors, graphrag, ontology
skills_middleware/ # Skill scanning / catalog middleware
utils/ # Shared utilities
ui/ # Next.js frontend
docs/ # Documentation site (Docusaurus)
docker-compose*.yaml # Canonical Docker Compose configurations
tests/ # Repo-level + RBAC tests
scripts/ # Utility scripts
charts/ # Helm charts
Find the Canonical Implementation
Start with the narrowest owning module; do not add a parallel implementation until you have checked the shared locations below.
| Need | Start here | Reuse before adding new code |
|---|---|---|
| UI page or API route | ui/src/app/ |
ui/src/components/, ui/src/lib/, ui/src/store/ |
| UI component | ui/src/components/ |
ui/src/components/ui/ and ui/src/components/shared/, then an existing component in the same feature area |
| UI selection control | ui/src/components/ui/{select,searchable-picker}.tsx |
Follow docs/docs/ui/selection-controls.md; reuse a domain picker before adding a base or custom listbox |
| UI state or browser data | ui/src/store/ |
Existing store and ui/src/lib/ helpers |
| MCP integration | ai_platform_engineering/mcp/<provider>/ |
ai_platform_engineering/mcp/common/ |
| Slack or Webex behavior | ai_platform_engineering/integrations/{slack_bot,webex_bot}/ |
The BFF/API contract and shared auth utilities |
| Dynamic/custom-agent runtime | ai_platform_engineering/dynamic_agents/ |
Its src/ modules and tests |
| RAG/ingestion | ai_platform_engineering/knowledge_bases/rag/ |
common/, server/, or ingestors/ as applicable |
| Authentication, authorization, or audit helpers | ai_platform_engineering/utils/{auth,audit_backends}/, ui/src/lib/authz/, ui/src/lib/rbac/, and ui/src/lib/audit/ |
Use the existing domain boundary; do not add direct OpenFGA checks outside an approved adapter |
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.
- 5d ago First seen · 129 lines · 1,712 tokens per session scan A ada77470fe98
ai-platform-engineering AGENTS.md is an instructions file published in the GitHub repository caipe-io/ai-platform-engineering (405 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,712 tokens to every session, about $0.0086 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
openhermit AGENTS.md
AGENTS.md instructions for HCF-STUDIOS/openhermit, covering openhermit workspace rules, general, code changes, testing and commits.
playbooks CLAUDE.md
Instructions for playbooks-ai/playbooks, covering claude.md, project overview, core architecture, framework components and key architectural insights.
agent-workflows AGENTS.md
Instructions for sjarmak/agent-workflows, covering agent instructions, quick reference, zfc enforcement, review checklist for agents and compliant patterns to preserve.
bureau CLAUDE.md
Claude Code instructions for Novadiem-Studio/bureau, covering novadiem studio ai framework — the bureau, canonical copy and drift, what this does, three-role model (notary / delegate / principal) and default entrypoint.
bureau AGENTS.md
AGENTS.md instructions for Novadiem-Studio/bureau, covering novadiem studio ai framework — the bureau, codex workspace instructions, canonical copy and drift, what this does and default entrypoint.
forge-orchestrator CLAUDE.md
Claude Code instructions for tarunms7/forge-orchestrator, covering workflow orchestration, 1. plan mode default, 2. subagent strategy, 3. self-improvement loop and 4. verification before done.