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/memory/project_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/project_daily_chat_test)<a href="https://agentmods.dev/skills/xaiht/tlamatini/project_daily_chat_test"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/project_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/project_daily_chat_test"><img src="https://agentmods.dev/badge/skills/xaiht/tlamatini/project_daily_chat_test.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.00855 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
project-daily-chat-test-skill 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 5d 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.
What it actually says
2026-06-05: Built a new Claude Code skill tlamatini-daily-chat-test at
.claude/skills/tlamatini-daily-chat-test/ (SKILL.md + harness/{config,questions,qualify,run_test}.py + README + requirements + .gitignore). Purpose: a daily automated regression that drives real Chrome via Playwright (channel=chrome, headed), logs into the Tlamatini chat, asks up to 1000 curated questions one-by-one, waits for + scrapes + qualifies each answer, and writes reports/run_<ts>/{results.jsonl,summary.json,report.md}.
Pinned run mode (user's explicit choice): Multi-Turn ON, ACPX/Ask-Execs/Exec-Report/Internet OFF — set on the toolbar by the harness. Because Multi-Turn ON = operator (tools really run), the 1000-question bank (questions.py, deterministic, asserts ==1000) is curated safe-to-execute (agent/system/self knowledge + benign read-only ops + general IT Q&A) — NO destructive prompts, no third-party scans, no mass GUI/message spawns. Qualify = heuristic gate on all + Anthropic LLM judge (claude-haiku-4-5-20251001) only on WEAK/FAIL, key auto-loaded from env/config.json/data.keys, degrades to skip if absent.
Hard-won DOM contract (in config.py): chat page is at /agent/agent/ (agent.urls is include()d under /agent/, and agent_page is path agent/ → double prefix; /agent/ alone is the LOGIN page again). Login = POST / with #id_username/#id_password. Send = fill #chat-message-input + click #chat-message-submit. Answer-complete signal = #chat-message-input no longer readOnly AND #wait-spinner removed from #chat-log (that's enableControlsAfterOperation() in agent_page_ui.js); intermediate "busy" banners keep it readOnly so they don't trigger a premature read. Answer text = last .message.bot-message .automated-message-body, filtering BUSY_MARKERS.
Proven live 10/10 + 150-subset runs vs the user's running server. Login creds are user-supplied (angela) via --user/--password or TLAMATINI_USER/TLAMATINI_PASS — installer default user/changeme does NOT work on the dev DB. Timing: ~61s/question under Multi-Turn → full 1000 ≈ 15–17h, so the harness is resumable (--resume), incremental, and supports --sample N (even cross-category spread) and --count. Not committed (user owns git). Server runs on 8000/8765/50051 (single-bound — never start a 2nd instance). See [[feedback_run_tlamatini_agents_visible]], [[feedback_state_constraints_upfront]].
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.
- 5d ago First seen · 26 lines · 46 tokens per session scan A 7c083a978bc2
project-daily-chat-test-skill is a skill published in the GitHub repository XAIHT/Tlamatini (16 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 855 once invoked, about $0.0002 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 2026-09-04.
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.
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.
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.
browser-automation
A set of instructions for controlling a web browser, testing web interfaces, and collecting information from websites that load content dynamically.
sc:webapp-testing
Test a web app end-to-end with Playwright: drive real flows, assert on visible state, catch console/network errors, and do visual + RTL/Hebrew checks. Covers writing resilient selectors (roles/text over CSS), waiting on conditions (never sleeps), screenshot diffing, and a quick smoke pass before shipping. Activate…