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/xaiht/tlamatini/gemini-mdgit clone --depth 1 https://github.com/XAIHT/TlamatiniWrote 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.
[](https://agentmods.dev/instructions/xaiht/tlamatini/gemini-md)<a href="https://agentmods.dev/instructions/xaiht/tlamatini/gemini-md"><img src="https://agentmods.dev/badge/instructions/xaiht/tlamatini/gemini-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.24121 | $0.24121 |
| Opus 5 | $0.12061 | $0.12061 |
| Sonnet 5 | $0.04824 | $0.04824 |
| Haiku 4.5 | $0.02412 | $0.02412 |
Grade C, and why
Tlamatini GEMINI.md scanned grade C with 3 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 6d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Every **transient** file Tlamatini writes lives under ONE directory — `Temp` at the application root (`<exe-dir>/Temp` frozen, `<repo-root>/Temp` source) — and **never** outside Tlamatini (no `C:\Temp`, no `%TEMP%`, no s Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
│ │ │ ├── zavuerer/ # Zavu unified-messaging bridge — ONE REST API key for SMS / WhatsApp / Telegram / Email / Voice (channel:auto ML smart-routing + auto-fallback); direct HTTP (stdlib urllib, no SDK, never imports agen Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Every pool-agent script (`ender.py` and all 50+ siblings in `agents/<name>/<name>.py`) installs a top-of-module `subprocess.Popen.__init__` monkey-patch — `_chg_guarded_init` — that defaults `creationflags` to `CREATE_ This is a copy
95% identical to Tlamatini CLAUDE.md — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 676 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ PRIVATE DATA GUARD — ABSOLUTE, NON-NEGOTIABLE, READ FIRST ⛔
NEVER REWRITE GIT HISTORY. EVER. IN THIS REPO, FOR ANY REASON.
- NO
rebase,commit --amend,reset --hardto drop commits,filter-branch,git filter-repo, BFG. - NO
push --force/--force-with-lease, NO deleting pushed tags, NO deleting remote refs. - TO REMOVE SENSITIVE / PRIVATE DATA: edit or delete the file, then make a NEW FORWARD COMMIT and push that. THE PAST STAYS UNTOUCHED.
- TAGS, PUSHES, AND
git logMUST ALWAYS REMAIN INTACT AND TRUTHFUL —git logMUST show the real history, made without lying, FOREVER. - PRIVATE INFORMATION MAY BE DELETED GOING FORWARD; THE HISTORY THAT RECORDED IT MUST NOT BE ERASED.
- IF ANY TOOL OR WORKFLOW WOULD REWRITE HISTORY, STOP AND TELL ANGELA FIRST.
Enforced by: test_private_data_guard.py (automated tests) + a global CAPS SessionStart banner (~/.claude/hooks/private_data_guard_banner.py) shown in every Claude Code session on this machine.
⛔ DO NOT TOUCH THE DB MECHANICS. EVER. (Angela, 2026-08-17, REAFFIRMED 2026-08-19) ⛔
THE DATABASE BACKUP / SET-DB CODE IS OFF LIMITS. DO NOT MODIFY IT, DO NOT "PROTECT" IT, DO NOT ADD A CHECK TO IT.
Angela's words, verbatim: "DON'T EVEN TRY TO TOUCH THE CODE ESPECIALLY ON THE DB MECHANICS."
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.
- 6d ago First seen · 676 lines · 24,121 tokens per session scan C 3964dcb14cf7
Tlamatini GEMINI.md is an instructions file published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed 2d ago), licensed MIT. It adds 24,121 tokens to every session, about $0.1206 per session on Opus 5. A static security scan graded it C with 3 findings (harvests environment variables, makes network calls, runs shell commands). It is 95% identical to Tlamatini CLAUDE.md, differing in 13 lines, and is treated as a copy.
Other instructions, from other repositories
keen-code AGENTS.md
AGENTS.md instructions for mochow13/keen-code, covering keen code, important guidelines, architecture and permission system.
juggler AGENTS.md
AGENTS.md instructions for juggler-ai/juggler, covering juggler, build / test / lint / dev, run them in the foreground, linting and tests.
LitosAiCodingAgent CLAUDE.md
Claude Code instructions for nitinmms/LitosAiCodingAgent, covering claude.md and avalonia (litos.gui).
keen-code CLAUDE.md
Claude Code instructions for mochow13/keen-code, a project described as: A context-aware terminal-based coding agent written in Go. Supports multiple-providers, MCPs, Subagents, Agent Skills, controllable tool output retention, hashline edits, and more.
mini-swe-agent copilot-instructions.md
Copilot instructions for SWE-agent/mini-swe-agent, covering style guide, test style, bad and good.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.