agentmods.dev

tsaagan: Instructions file for Codex

AGENTS.md

tsaagan AGENTS.md is an instructions file for Codex, OpenCode from michaelolmos/tsaagan. It costs 1,227 tokens per session, scanned A, original, MIT.

A set of operating instructions for Tsaagan, a tool that can work with websites through APIs, real browsers, or browser automation.

In plain words
What is it for?
It guides API detection and calls, secure key storage, browser use for logged-in sites, and automation through extension, macOS, or Playwright-based modes.
Why use it?
It tells the agent which access method to try first and requires checking verification details after actions that change data.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

This is michaelolmos/tsaagan's own configuration. It tells Codex and OpenCode how to work on tsaagan itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tsaagan configures →

not rated 2repo 9d ago A scan 1,227 tokens original MIT
View source ↗ michaelolmos/tsaagan
Reuse

Borrowing it

Nothing to install: this file belongs to michaelolmos/tsaagan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/michaelolmos/tsaagan/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/michaelolmos/tsaagan

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 tsaagan AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/michaelolmos/tsaagan/agents-md/github.svg)](https://agentmods.dev/instructions/michaelolmos/tsaagan/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/michaelolmos/tsaagan/agents-md"><img src="https://agentmods.dev/badge/instructions/michaelolmos/tsaagan/agents-md/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.

agentmods 80×15 button for tsaagan AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/michaelolmos/tsaagan/agents-md"><img src="https://agentmods.dev/badge/instructions/michaelolmos/tsaagan/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,227 This file is loaded in full into every session.
When invoked 1,227 The same file — it is already loaded in full.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01227 $0.01227
Opus 5.5 $0.00491 $0.00491
Sonnet 5.5 $0.00245 $0.00245
Haiku 4.5 $0.00123 $0.00123

Measured 2mo ago against content hash 3ca4de1ac03a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tsaagan 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 2mo 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — how to drive Tsaagan

This file tells any AI agent (Claude Code, Codex/ChatGPT CLI, Cursor, etc.) how to use Tsaagan well. Read SOUL.md for why; this is how.

tsaagan = node tsaagan.js. Every command prints JSON. Mutating actions return a verify block — read it; don't assume success.

Pick the lightest layer that does the job

  1. API layer first. If the site has an official API, use it — fastest, robust, no UI to drive at all.
    • tsaagan api detect=<url> → is there a known API?
    • tsaagan api service=<x> path=/… method=… → call it with a stored key.
    • First time: store the key — tsaagan vault set service=<x> secret=… (Keychain). Tsaagan can even browse the site's developer settings to create the key, then vault set it (see docs/API.md).
  2. Real-browser layer for sites without an API or behind a login:
    • extension mode (any OS) — trusted input, viewport coords, no debug port. Best for sites that ignore synthetic input. See docs/EXTENSION.md.
    • native mode (macOS) — real Chrome via AppleScript + OS input.
  3. CDP layer (fresh/clone/live) — Playwright; great for the broad middle of the web (dashboards, SaaS). Note: CDP input is isTrusted=false, so a minority of strict sites ignore it — use native/extension there.

The loop (every browser step)

OBSERVE → THINK → ACT → VERIFY → RECOVER

  1. tsaagan snapshot — read the accessibility tree; act on stable [ref=eN].
  2. Pick one goal; ≤3 actions before re-observing (the page changes after action 1).
  3. Act: tsaagan click ref=e5 expectText="…", tsaagan type ref=e3 text="…" submit=true. Always pass expectText=/expectGone= so the step self-verifies.
  4. Read the verify block (urlChanged, expectTextFound, newConsoleErrors, failedRequests). That's how you know it worked.
  5. On ok:false: re-snapshot, retry with a fresh ref, or change approach. Ref actions self-heal once automatically.

Read the full file on GitHub · 90 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. 2mo ago First seen · 90 lines · 1,227 tokens per session scan A 3ca4de1ac03a

Subscribe to this mod's changes

tsaagan AGENTS.md is an instructions file published in the GitHub repository michaelolmos/tsaagan (2 stars, last pushed 9d ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0049 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 2026-08-31.

Browser automationLLMaccessibilityagenticai-agentbrowser-agentbrowser-automation
Related

tsaagan AGENTS.md compared with instructions from other repositories

tsaagan AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tsaagan AGENTS.mdmichaelolmos/tsaaganInstructions file29d agoMITA1,227Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot