synth-ai AGENTS.md

synth-ai AGENTS.md is an instructions file for Codex, OpenCode from synth-laboratories/synth-ai. It costs 1,558 tokens per session, scanned A, original, MIT.

A set of instructions for Synth AI, a Python package and research software project. It explains which package owns the research software, how compatibility with older imports is maintained and what checks are required before a release.

In plain words
What is it for?
Use it when changing the research SDK, backend integrations, public Python interfaces, package releases or launch checks.
Why use it?
It prevents duplicated implementations and unreleased or untested code from being presented as ready for customers.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/synth-laboratories/synth-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/synth-laboratories/synth-ai

Made for: Codex, OpenCode.

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.

agentmods badge for synth-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/synth-laboratories/synth-ai/agents-md.svg)](https://agentmods.dev/instructions/synth-laboratories/synth-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/synth-laboratories/synth-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/synth-laboratories/synth-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,558 This file is loaded in full into every session.
When invoked 1,558 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01558 $0.01558
Opus 5 $0.00779 $0.00779
Sonnet 5 $0.00312 $0.00312
Haiku 4.5 $0.00156 $0.00156

Measured 4d ago against content hash 5f3c4e6f9fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

synth-ai 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 4d 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.

AGENTS.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Notes

  • PlanetScale now supports PostgreSQL. Treat PlanetScale as Postgres for schema, SQL, and migrations.

CRITICAL: Prod launch checklist

Any synth-ai PyPI release tied to a launch must clear the Packages and SDK sections of ../synth-dev/launch_checklist.md — fresh-venv install smoke, typed error imports, backend parity (version-contract), no unreleased local changes claimed in launch copy. Record published version + smoke output as proof.

CRITICAL: Managed Research SDK ownership

synth-ai is the canonical home for Managed Research SDK/client, MCP server, models, transport, schemas, and public SynthClient().research interfaces. The standalone managed-research package is a compatibility shim only during the retirement window.

  • Keep backend as the contract authority; do not invent SDK behavior that bypasses backend routes, hosted MCP, or the control-plane facade.
  • Preserve legacy import and CLI compatibility through shim modules when moving public surfaces into synth-ai.
  • Customer-facing examples should prefer from synth_ai import SynthClient.

Coding Style

Follow the Synth Style guide: specifications/tanha/references/synthstyle.md (sibling repo).

  • Docstrings link to specs. Use /// See: specifications/tanha/... (Rust) or # See: specifications/tanha/... (Python) on non-trivial public functions/modules.
  • All errors handled. Rust: thiserror, never unwrap(). Python: never swallow exceptions.
  • Naming. No abbreviations. Units last: timeout_ms, retry_count_max.
  • Comments say why. Code says what. Comments say why. Specs say the full story.

CRITICAL: Running The Backend Locally

Do not hand-roll the local stack. Use the synth-dev repo (sibling checkout under ~/Documents/GitHub/).

cd ../synth-dev
./scripts/local.sh up slot1

See ../synth-dev/README.md for prerequisites (Colima, uv, secrets), fixed slot port maps, and commands (local.sh status, doctor, down, etc.).

Read the full file on GitHub · 126 lines

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.

  1. 4d ago First seen · 126 lines · 1,558 tokens per session scan A 5f3c4e6f9fa6

Subscribe to this mod's changes

synth-ai AGENTS.md is an instructions file published in the GitHub repository synth-laboratories/synth-ai (82 stars, last pushed 13d ago), licensed MIT. It adds 1,558 tokens to every session, about $0.0078 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.