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/onesimplecode/agent-engineering-standards/agents-mdgit clone --depth 1 https://github.com/onesimplecode/agent-engineering-standardsWhat 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 | $0.07592 | $0.07592 |
| Opus 5 | $0.03796 | $0.03796 |
| Sonnet 5 | $0.01518 | $0.01518 |
| Haiku 4.5 | $0.00759 | $0.00759 |
Grade A, and why
agent-engineering-standards 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 yesterday.
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 — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Public Agent Conventions
These conventions are the portable, tool-neutral layer of the AI Engineering Standards. They can be read by Claude Code, Cursor, Codex, Gemini CLI, or any agent that accepts repository instructions.
The goal is not to make agents more verbose. The goal is to make agent-assisted software work bounded, reviewable, and auditable.
Core Rules
Requirements Syntax
Write requirements in EARS style when they become acceptance criteria:
When
<trigger>, the system shall<observable behavior>.
Avoid vague words like "should" once a requirement is active.
Data Routing (TR-SEC-003)
Data that can identify a person, expose a secret, or reveal private business context must be handled by a local/private workflow unless an ADR documents an explicit exception.
Cloud-backed agents may work on public docs, public code, synthetic examples, and low-risk drafting. They must not receive secrets or private datasets.
Loop Contracts (TR-AGT-003)
Every multi-step agent node declares four fields before implementation:
- Input schema — expected state or data.
- Output schema — produced state or data.
- Exit condition — observable evidence that the node is done.
- Resource budget — max iterations, token budget, or wall-clock timeout.
Missing any field means the design is incomplete.
The exit condition must be verified by deterministic evidence when the agent changes persistent state, writes files, sends messages, or calls tools with side effects (TR-TEST-006).
See examples/engine-interface/ for a concrete reference implementation: a
SearXNG-inspired multi-source polling pattern where source_name (identity),
default_timeout (budget), a never-raising fetch() (exit condition), and a
normalized list[Result] (output schema) map directly onto the four fields above.
MCP Tool Annotations (TR-AGT-003, field 5)
When a node is exposed as an MCP tool, declare four hint flags describing its blast radius. These are advisory hints to MCP clients (Claude Code, Cursor, opencode) — the MCP protocol does not enforce them, so declare them accurately regardless.
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.
- yesterday First seen · 639 lines · 7,592 tokens per session scan A f3c416b4833a
agent-engineering-standards AGENTS.md is an instructions file published in the GitHub repository onesimplecode/agent-engineering-standards (3 stars, last pushed 4d ago), licensed MIT. It adds 7,592 tokens to every session, about $0.0380 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
sdlc-quality AGENTS.md
Instructions for zircote-plugins/sdlc-quality, covering agents.md - openai codex guidelines, project identity, quick context, agent guidelines and 1. understand the domain model.
sdlc-quality copilot-instructions.md
Instructions for zircote-plugins/sdlc-quality, covering copilot instructions for sdlc plugin, project overview, repository structure, key conventions and rfc 2119 terminology.
deliberate CLAUDE.md
Instructions for angad-kandhari/deliberate, covering deliberate, repo structure, sibling repo and conventions.
deliberate AGENTS.md
Instructions for angad-kandhari/deliberate, covering agents.md — deliberate, core discipline (apply to every non-trivial task), verify before you claim done and load the matching discipline.
context-engineering AGENTS.md
Instructions for fending/context-engineering, covering agents.md, what this project is, structure, standards and navigation.
cc-agents-md CLAUDE.md
Claude Code instructions for GeiserX/cc-agents-md, covering claude.md — cc-agents-md, tech stack, development, install dependencies and run tests.