What is arch-experience-contract?

A planning workflow for defining what good performance means for an AI agent before or early in development. It records the users, common requests, success checks, response limits, and other measurable expectations.

Use it to set success criteria for major intents, estimate traffic and costs, define latency and model-call limits, and guide choices about prompts, memory, tools, and voice.

Terms such as “better” or “optimized” are not useful unless the team agrees how to measure them. A written contract gives later design and tuning decisions a clear target.

arch-experience-contract — Skill for Codex by Koredotcom

Install

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.

Any agent

npx skills add Koredotcom/agents-mcp-tools --skill arch-experience-contract

Clone the repo

git clone --depth 1 https://github.com/Koredotcom/agents-mcp-tools

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-experience-contract/github.svg)](https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-experience-contract)

Your own site

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-experience-contract"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-experience-contract/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/koredotcom/agents-mcp-tools/arch-experience-contract"><img src="https://agentmods.dev/badge/skills/koredotcom/agents-mcp-tools/arch-experience-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 794 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00087	$0.00794
Opus 5.5	$0.00035	$0.00318
Sonnet 5.5	$0.00017	$0.00159
Haiku 4.5	$0.00009	$0.00079

Measured 1mo ago against content hash a6523506b4d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

arch-experience-contract 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 1mo 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.

skills/arch-experience-contract/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Experience contract

Every later decision (topology, model, history mode, guardrails, voice settings) is checked against this contract. Without it, nobody can say when the agent is good enough, and optimization has no target. Write it in week one.

Gather the evidence

Read the project's agents and topology: debug_get_flow_graph (after debug_load_agent, or with projectId, sessionId and source: "historical") (Mermaid, includeAppGraph), platform_package_model on the exported package (path).
If sessions exist, use debug_session_history (action: "list", range: "7d") and platform_analytics to estimate intent share, turns per conversation, model calls per turn and latency. Analyze a few representative sessions with debug_analyze_session.
Ask the developer for what the data cannot show: business success criteria, compliance steps, channels and languages.

Output contract

Story: two or three sentences on what the agent is for and who uses it.
Contract table, one row per top intent (the 5–10 that make up most traffic): intent | share of sessions | example caller utterance | success definition you can check in a transcript or tool call | channel | p50 and p95 first-response latency target | model calls per turn budget | input tokens per turn budget | steps that must be deterministic | failure behavior.
Measured or inferred: mark every number. Measured numbers cite the sessions; inferred numbers say what they were inferred from.
Gap list: the intents furthest from target today, each with one example session ID.
Evidence plan: which eval set will prove each line (see arch-eval-catalog).
Glossary for any platform term used.
Confidence and gaps: which numbers rest on few sessions, and what data was not available.

Do not shorten the table. If long, write it to docs/experience-contract.md in the project folder.

Why budgets drive design

Every design choice spends from the same budget. Show the developer the cost before they commit:

Read the full file on GitHub · 58 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

agents/openai.yaml 328 B

Changes

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.

1mo ago First seen · 58 lines · 87 tokens per session scan A a6523506b4d3

Subscribe to this mod's changes

arch-experience-contract is a skill published in the GitHub repository Koredotcom/agents-mcp-tools (4 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 794 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-09.

Building agents Planning

arch-experience-contract next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
arch-experience-contractKoredotcom/agents-mcp-tools	Skill	4	1mo ago	MIT	A	87	Codex
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	80k	6d ago	MIT	A	200	Claude Code, Codex
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex