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/stoa-platform/stoa/agents-mdgit clone --depth 1 https://github.com/stoa-platform/stoaWhat 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 | $0.00529 | $0.00529 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
stoa 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.
What it actually says
AGENTS.md — STOA Platform
This repo uses CLAUDE.md as the canonical AI agent contract. AGENTS.md exists
as the cross-agent entry point for any AI coding assistant (Claude Code, Codex,
Cursor, Aider, etc.).
Contract
AI agents working in this repository must:
- Read
CLAUDE.mdat the repo root for project rules, architecture, runtime versions, workflow, and GO/NOGO gates. It is the single source of truth — this file does not duplicate its content to avoid drift. - Read the component-scoped
CLAUDE.mdinside the directory you are editing (e.g.stoa-gateway/CLAUDE.md,control-plane-api/CLAUDE.md,control-plane-ui/CLAUDE.md) when touching that service. - Load
.claude/docs/<topic>.mdon demand when a rule inCLAUDE.mdreferences it. These docs are protocols, examples, and gotcha tables — never auto-loaded, only pulled in when the topic is in scope. - Follow the same rules regardless of the tool brand. The
.claude/storage path is a naming convention, not a tool lock-in; any AI agent is expected to honor the rules defined there.
Architecture (quick reference)
CONTROL PLANE (Cloud) DATA PLANE (On-Premise)
┌────────────────────────────┐ ┌──────────────────────┐
│ Portal Console API Auth │ ←sync→ │ STOA GW webMethods │
│ (React) (React) (Py) (KC) │ │ (Rust) Kong/Envoy │
└────────────────────────────┘ └──────────────────────┘
For component paths, runtime versions, RBAC roles, rules, skills, and repo
map, see CLAUDE.md.
Agent-facing API doctrine
When touching an API operation exposed to agents, load the canonical rule in
CLAUDE.md and .claude/docs/uac-llm-ready.md:
UAC describes.
MCP projects.
Smoke proves.
Historical note
The Python mcp-gateway/ service was retired in Feb 2026 and superseded by
stoa-gateway/ (Rust). Any reference to mcp-gateway in older docs or
comments is historical.
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 · 53 lines · 529 tokens per session scan A f1d34ef93fc1
stoa AGENTS.md is an instructions file published in the GitHub repository stoa-platform/stoa (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 529 tokens to every session, about $0.0026 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
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
ant-design-pro CLAUDE.md
Claude Code instructions for ant-design/ant-design-pro, covering claude.md, project, commands, critical rules and architecture essentials.
apisix AGENTS.md
Instructions for apache/apisix, covering apache apisix — agent instructions and security model.
plano CLAUDE.md
Instructions for katanemo/plano, covering claude.md, build & test commands, rust — wasm plugins (must target wasm32-wasip1), rust — brightstaff binary (native target) and rust — tests, format, lint.
tingly-box CLAUDE.md
Instructions for tingly-dev/tingly-box, covering tingly-box, guideline, ux-first (highest priority), frontend and icons.
aisix CLAUDE.md
Instructions for api7/aisix, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.