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/dlapiduz/iaf/claude-mdgit clone --depth 1 https://github.com/dlapiduz/iafWrote 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/dlapiduz/iaf/claude-md)<a href="https://agentmods.dev/instructions/dlapiduz/iaf/claude-md"><img src="https://agentmods.dev/badge/instructions/dlapiduz/iaf/claude-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 5.1 | $0.01308 | $0.01308 |
| Opus 5 | $0.00654 | $0.00654 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
iaf CLAUDE.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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IAF - Intelligent Application Fabric
Platform Vision
IAF is an agentic application platform — infrastructure purpose-built for AI agents to deploy, run, and manage applications on Kubernetes.
Key design principles every contributor must understand:
- Agentic-first: The primary users are AI agents, not humans. APIs, tools, and error messages must be unambiguous, self-describing, and recoverable without human intervention.
- Short- and long-lived workloads: IAF must support both ephemeral apps (a quick demo, a one-off task) and persistent production services. Lifecycle management, cleanup, and resource limits matter.
- Multi-tenancy at every layer: Multiple agents (and the humans/organizations behind them) share the same cluster. Namespace isolation, RBAC, and resource quotas are not optional features — they are core invariants.
- Enterprise-ready security: IAF will be used by small teams and large organizations alike. Security decisions made now are hard to undo. Every feature must be designed with the assumption that a compromised or misbehaving agent must not be able to affect other tenants.
- Shared resources, clear boundaries: Agents share the cluster, the registry, the ingress controller, and the build system. Any feature that touches shared infrastructure must account for fair use, rate limiting, and blast radius.
Security non-negotiables:
- Agent sessions are isolated in their own Kubernetes namespace — never bypass this.
- No cross-namespace access to secrets, services, or storage.
- All API and MCP endpoints require authentication — never add unauthenticated routes that touch cluster state.
- Containers run as non-root. Never relax this in platform-managed workloads.
- User-supplied values (app names, env vars, file paths, image references) must be validated and sanitized before use in Kubernetes objects or shell commands.
- Least privilege: the platform's own service account should only have the permissions it needs — review RBAC before adding new verbs or resources.
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 · 86 lines · 1,308 tokens per session scan A 8037f44e1678
iaf CLAUDE.md is an instructions file published in the GitHub repository dlapiduz/iaf (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,308 tokens to every session, about $0.0065 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 2026-08-31.
Other instructions, from other repositories
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).
cron-mcp CLAUDE.md
Claude Code instructions for Shreyas-Profile/cron-mcp, covering deploying cron-mcp to hetzner + regiq.in, server (shared with the rest of the globalion mcp fleet), deploy a new version, first-time subdomain wiring (cron.regiq.in) and env vars.
Railway-mcp CLAUDE.md
Claude Code instructions for Travis-Gilbert/Railway-mcp, covering railway mcp server, quick reference, file map, architecture and key patterns.
equinix-fabric-mcp CLAUDE.md
Claude Code instructions for sliuuu/equinix-fabric-mcp, covering claude.md — equinix-fabric-mcp, canonical files, auth, add equinixclientid and equinixclientsecret and running.