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 commands/y49/tlive/statusgit clone --depth 1 https://github.com/y49/tliveWhat 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 | $0.00012 | $0.00222 |
| Opus 5 | $0.00006 | $0.00111 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
status 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 yesterday.
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
Run tlive status and show the output to the user verbatim. If the mode:
line says notify (the default), point out that remote approval is off — tlive
only watches + notifies, and tool prompts stay local; enable phone Allow/Deny
with tlive mode full. full means remote approval is on for the main
session; all means sub-agent approvals are held too (no terminal dialog for
a held one until the window ends — only worth it when nobody is at the
keyboard); off disables tlive entirely. If the Codex line says degraded or
off, explain: Codex
approvals are local-only right now (the native prompt still works; nothing is
ever auto-run) — off usually means codex is not on PATH, degraded means the
app-server child keeps failing (see ~/.tlive/codex-appserver.log).
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.
- yesterday First seen · 16 lines · 12 tokens per session scan A 83e59562ea23
status is a command published in the GitHub repository y49/tlive (206 stars, last pushed 11d ago), licensed MIT. It adds 12 tokens to every session and 222 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.
test-feature
Generate comprehensive tests for a KMP feature.
review-feature
Review a KMP feature against architecture patterns and spec.
specify
Create or update the feature specification from a natural language feature description.
dead-code-scan
Scan for dead code, unused imports, duplicates, and zombie code across the project.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.