Borrowing it
Nothing to install: this file belongs to tellahq/opensession. 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/tellahq/opensession/main/.agents/skills/verify-opensession/SKILL.mdgit clone --depth 1 https://github.com/tellahq/opensessionWrote 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/tellahq/opensession/verify-opensession)<a href="https://agentmods.dev/skills/tellahq/opensession/verify-opensession"><img src="https://agentmods.dev/badge/skills/tellahq/opensession/verify-opensession.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 | $0.00034 | $0.01633 |
| Opus 5 | $0.00017 | $0.00816 |
| Sonnet 5 | $0.00007 | $0.00327 |
| Haiku 4.5 | $0.00003 | $0.00163 |
Grade A, and why
verify-opensession scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify Open Session
Use this skill for user-visible work in Open Session's primary client, the server-hosted web UI and phone PWA. The repository also ships Electron, native Swift, and Chrome extension clients. This skill does not prove their client-specific behavior.
Never point these commands at https://os.tella.dev, port 3850, or scripts/frontend-dev.ts. Those paths use production state. The launcher below starts a fresh demo instance with private gateway and SessionKernel ports, process groups, a browser profile, and a state directory.
Launch
This recipe currently requires Linux with a reachable systemd user manager, Google Chrome, Xvfb, ss, and jq. From the repository root, install dependencies if node_modules is absent, then start one run:
bun install --frozen-lockfile
export RUN_ID="verify-$(date +%Y%m%d-%H%M%S)-$$"
./.agents/skills/verify-opensession/bin/verify-opensession launch "$RUN_ID"
The command prints APP_URL, STATE_DIR, and EVIDENCE_DIR. It starts the real Bun gateway and SessionKernel with a shared scratch credential, OPENSESSION_DEV=1, OPENSESSION_DEMO=1, and a disposable OPENSESSION_STATE_DIR under /tmp. The demo seed supplies sessions, transcripts, a repository, pull request state, automations, and a paused goal. External agents, schedulers, webhooks, executor work, and live credentials stay off.
The instance is ready when launch returns successfully. Its log remains at /tmp/opensession-verify-$RUN_ID/server.log until cleanup.
Teardown what this run started:
./.agents/skills/verify-opensession/bin/verify-opensession cleanup "$RUN_ID"
Run cleanup after failed attempts too. Each run has a separate port, browser profile, and state directory, so concurrent runs are safe when their RUN_ID values differ.
Doctor
Run this before driving the UI and whenever the page or browser looks wrong:
./.agents/skills/verify-opensession/bin/verify-opensession doctor "$RUN_ID"
Doctor checks the exact server PID, port owner, launch commit, boot ID, disposable state environment, auth status, health endpoint, and private CDP browser. A changed checkout commit fails the check because the running backend may no longer match the files under review. Clean up and launch again rather than driving a stale process.
What ships with it
8 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.
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.
- 3d ago First seen · 124 lines · 34 tokens per session scan A 54f001380930
verify-opensession is a skill published in the GitHub repository tellahq/opensession (355 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,633 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 2026-09-03.
Other skills, from other repositories
browse
Drive a real browser through Aside: open a page, read it, click through a flow, take screenshots, check console errors. (gstack).
playwright-cli
A command-line tool for controlling Chromium, Firefox, and WebKit browsers, including navigation, page interaction, screenshots, PDFs, and recorded actions.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
browser-qa
A browser-based quality check for deployed web pages and user flows. It uses browser automation to test rendering, navigation, forms, interactions, responsive behaviour, and accessibility-related issues.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.