Borrowing it
Nothing to install: this file belongs to XAIHT/Tlamatini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/XAIHT/Tlamatini/main/.claude/skills/tlamatini-daily-chat-test/SKILL.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/skills/xaiht/tlamatini/tlamatini-daily-chat-test)<a href="https://agentmods.dev/skills/xaiht/tlamatini/tlamatini-daily-chat-test"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini-daily-chat-test/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.
<a href="https://agentmods.dev/skills/xaiht/tlamatini/tlamatini-daily-chat-test"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/tlamatini-daily-chat-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 148 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium MCP Rug Pull · line 144 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
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 | $0.00125 | $0.03330 |
| Opus 5 | $0.00063 | $0.01665 |
| Sonnet 5 | $0.00025 | $0.00666 |
| Haiku 4.5 | $0.00013 | $0.00333 |
Grade A, and why
tlamatini-daily-chat-test scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:8000/ How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tlamatini Daily Chat Test
A self-contained Playwright harness lives in harness/ next to this file. It opens
real Chrome, logs into Tlamatini, and asks up to 1000 curated questions to
the chat one at a time — typing, sending, waiting for the answer to finish, scraping
it, and qualifying it — then writes a Markdown report + JSON summary.
This is the operator-mode regression the user wants run daily.
⛔ FORBIDDEN: headless tests — ALL TESTS MUST BE VISIBLE (Angela, HARD RULE, 2026-07-07)
HEADLESS / INVISIBLE AUTOMATED TESTS ARE FORBIDDEN. This test ALWAYS runs in a VISIBLE, HEADED real Chrome on Angela's desktop — she MUST see every step live.
--headless is disabled in run_test.py (it is ignored and forced back to headed). Never try to run this or any test invisibly. Launch it inside a VISIBLE foreground window (Start-Process powershell -NoExit …, dangerouslyDisableSandbox:true), never run_in_background. Verify steps with FULL-SCREEN screenshots (whole desktop, taskbar clock visible) and NEVER record a stale/transient/timed-out answer as a pass.
See memory feedback_forbidden_headless_visible_tests and the visible runners harness/discoverer_1000.py (Discoverer), harness/pdfer_nuance_visible.py (PDFer) and harness/dialog_policy_visible.py.
harness/pdfer_nuance_visible.py is the 2026-09-06 proof of PDFer's nuance / typography / layout overhaul. It spawns the REAL pdfer.py the way the pool does (a copied runtime dir + a written config.yaml, never an import), renders the same content under different treatments, audits every produced PDF against the file on disk with PyMuPDF, opens each one on screen, and photographs the whole desktop with Shoter. Its seventh case deliberately renders the torture tables through the OLD xhtml2pdf engine so the before/after sits together rather than being a claim: measured 2026-09-06, the new engine is CLEAN and the old one shows 8 overlapping text pairs on the same tables while reporting err=0. A case passes only if the PDF exists AND the audit is clean AND the reported design fields match what was asked for AND Shoter produced a photo — a missing photo is a FAILURE, never a silent pass. ⚠️ It drives the agent in the repo (C:\Development\XAIHT\Tlamatini) on purpose: the Django server on this machine runs from a DIFFERENT install (C:\Development\Tlamatini), so a chat-GUI route would exercise the OLD PDFer until that install is synced. The 2026-08-16 dialog-dismissal proof opens each real dialog in headed Chrome, presses Escape, and confirms it closed with the same meaning as its ✕. It also proves that the sealed updater refuses Escape / Ctrl+F4 / F5 while a download is in progress through a window.__tlmSealCanary, so "the dialog is gone" and "F5 worked" can never look identical. It never starts a real update: it calls seal('update') to reproduce the exact policy state.
What ships with it
34 files 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.
- .gitignore 157 B
- harness/acp_backend_banner_test.py 14 KB runs code
- harness/acp_backend_banner_test.py.antes_shoter 13 KB
- harness/acp_dialog_full_sweep.py 18 KB runs code
- harness/acp_dialog_theme_visible.py 11 KB runs code
- harness/ask_execs_regression.py 28 KB runs code
- harness/ask_execs_regression.py.antes_shoter 28 KB
- harness/bulk_toggle_behaviour.py 13 KB runs code
- harness/bulk_toggle_visible.py 8.1 KB runs code
- harness/cancel_regression.py 23 KB runs code
- harness/cancel_regression.py.antes_shoter 23 KB
- harness/config.py 5.9 KB runs code
- harness/cyber_watchdog_test.py 22 KB runs code
- harness/dialog_policy_visible.py 23 KB runs code
- harness/dialog_theme_visible.py 11 KB runs code
- harness/discoverer_1000.py 1.5 KB runs code
- harness/discoverer_1000.py.antes_shoter 20 KB
- harness/flowcreator_wizard_e2e.py 16 KB runs code
- harness/googler_dork_hunt.py 12 KB runs code
- harness/latexer_openmp_e2e.py 14 KB runs code
- harness/latexer_stepbystep_5.py 39 KB runs code
- harness/mcp_playwright_suite.py 11 KB runs code
- harness/pdfer_nuance_visible.py 22 KB runs code
- harness/playwrighter_run.py 6.5 KB runs code
- harness/qualify.py 8.0 KB runs code
- harness/questions.py 21 KB runs code
- harness/README.md 5.6 KB
- harness/requirements.txt 340 B
- harness/run_test.py 32 KB runs code
- harness/shoter_shot.py 4.0 KB runs code
- harness/step_by_step_catalog.py 16 KB runs code
- harness/step_by_step_catalog.py.antes_shoter 16 KB
- harness/talk_test.py 16 KB runs code
- harness/wrapped_questions.py 15 KB runs code
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.
- 4d ago Changed · +2 lines 15632d975439
- 12d ago First seen · 157 lines · 125 tokens per session scan A 47c4b0c1c879
tlamatini-daily-chat-test is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed today), licensed MIT. It adds 125 tokens to every session and 3,330 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
run-dashboard-e2e-local-changes
Run Playwright E2E (tests/e2e/) against the docker/ all-in-one harness so it reflects LOCAL code changes, not a stale cached image.
frontend-explorer
An exploratory browser test that uses a real browser and a first-time-user perspective to find where people get stuck or do not understand a web product. Each finding includes the text seen on screen and screenshot evidence, ordered by how much it blocks progress.
playwright
Use globally installed playwright-cli for browser automation, UI inspection, screenshots, Playwright test debugging, or test generation. Trigger when a task needs browser interaction or test repair. Do not use for generic tests, web search, non-browser docs, or API-only work.
browser-automation
A set of instructions for controlling a web browser, testing web interfaces, and collecting information from websites that load content dynamically.
webapp-testing
Verify a local web app in a real browser with page, element, click, form, console and screenshot evidence. Use after a build or UI change; do not implement features or publish deployments with this skill.