A live tester for Shiki's terminal user interface, or TUI—a text-based interface displayed in a terminal window. It builds the program, drives it with real key presses through tmux, and checks the captured screen.

Use it to verify TUI features and keybindings, reproduce interface bugs, and compare documented behavior with the actual footer, layout, or modal screen.

A keybinding or screen claim can look correct in code but fail when the program runs. This tests the behavior in an isolated environment and reports what appeared.

How sazardev/shiki configures OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sazardev/shiki. 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/sazardev/shiki/main/.opencode/agent/tui-tester.md

Clone the repo

git clone --depth 1 https://github.com/sazardev/shiki

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/sazardev/shiki/tui-tester/github.svg)](https://agentmods.dev/agents/sazardev/shiki/tui-tester)

Your own site

<a href="https://agentmods.dev/agents/sazardev/shiki/tui-tester"><img src="https://agentmods.dev/badge/agents/sazardev/shiki/tui-tester/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/sazardev/shiki/tui-tester"><img src="https://agentmods.dev/badge/agents/sazardev/shiki/tui-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 428 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.00428
Opus 5.5	$0.00034	$0.00171
Sonnet 5.5	$0.00017	$0.00086
Haiku 4.5	$0.00008	$0.00043

Measured 1mo ago against content hash 80d8c33451b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tui-tester 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 1mo 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.

.opencode/agent/tui-tester.md · 25 lines

What it actually says

You are the live-TUI tester for the shiki codebase.

Load the tui-tmux-test skill with the skill tool and follow its workflow exactly.
The task tells you which feature/binding to verify (e.g. "zen mode via leader z", "outline modal via o and Ctrl+O", or a bug to reproduce). If the task names a keybinding, first confirm the default key in shiki-config/src/config.rs (e.g. zen_mode = "z") and the action in shiki-tui/src/keybindings.rs so you know the exact keys to send — then verify live.
Isolate ALWAYS: throwaway root under /tmp, XDG_CONFIG_HOME/XDG_DATA_HOME overridden, seed data via the CLI (shiki notebook create personal, shiki new ... -n personal --body ...).
Drive the TUI with tmux send-keys and assert on tmux capture-pane:
- Report the footer status message, layout shape, and any modal contents verbatim.
- A verdict: "verified live" (with the observed screen evidence) or "mismatch" (doc says X, screen shows Y — quote both).
Clean up: kill the tmux session and remove the temp root. Never leave a session or stray dirs.
If the binary doesn't build or the TUI errors, report that as the result with the error output — do not improvise around it.

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.

1mo ago First seen · 25 lines · 84 tokens per session scan A 80d8c33451b1

Subscribe to this mod's changes

tui-tester is an agent published in the GitHub repository sazardev/shiki (335 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 428 once invoked, about $0.0003 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 2026-09-10.

E2E testing Git and workflow Productivity Testing cli markdown note-taking notes

tui-tester next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
tui-testersazardev/shiki	Agent	335	yesterday	MIT	A	84	OpenCode
Metis VerifierWholiver/metis	Agent	438	7d ago	MIT	A	36	Claude Code
test-automatorechoVic/blade-code	Agent	181	24d ago	MIT	A	46	Claude Code
frontend-specialistInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	61	Claude Code
testerInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	38	Claude Code
e2e-runnerrohitg00/skillkit	Agent	1.6k	5mo ago	Apache-2.0	A	25	Claude Code
scaffolderfuxicodex/Fuxi	Agent	3.2k	17d ago	none	A	49	Claude Code

shiki: Agent for OpenCode