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/lanegrid/agtrace/watchgit clone --depth 1 https://github.com/lanegrid/agtraceWhat 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 | $0.00000 | $0.00295 |
| Opus 5 | $0.00000 | $0.00148 |
| Sonnet 5 | $0.00000 | $0.00059 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
watch 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 2d 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
agtrace watch
Live "top"-style dashboard for AI coding agent sessions.
Overview
agtrace watch provides a real-time TUI (Terminal User Interface) that shows session vitals as your AI coding agent runs:
- Context window usage and pressure
- Current turn and recent activity
- Tool usage signals
- Token counts and cost telemetry
Usage
agtrace watch [OPTIONS]
Behavior
Auto-detection
watch can be started before or after your AI coding agent:
- No active session: Stays in waiting mode (or opens the latest session if available)
- New session detected: Automatically switches to the new session
- No restart needed: Keep
watchrunning across multiple agent sessions
Key Features
Live Session Vitals
The dashboard displays:
- Context Usage: Percentage of context window used, with warnings as you approach compaction
- Current Turn: The active conversation turn number
- Recent Activity: Latest tool calls and agent actions
- Token Telemetry: Input/output tokens and estimated costs
Always-On Monitoring
Keep watch running in a terminal pane or tmux session. It will automatically pick up new sessions without requiring a restart.
See Also
- session - Inspect historical sessions
- FAQ: CWD-Scoped Monitoring
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.
- 2d ago First seen · 47 lines · 0 tokens per session scan A d473785f0207
watch is a command published in the GitHub repository lanegrid/agtrace (59 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 295 tokens. 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
spec-design
Create comprehensive technical design for a specification.
add-agent
引导新增一个 Agent 适配器。用法 /add-agent.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
speckit.opsmill.retrospect
Run a session retrospective that surfaces context-management gaps and routes them to approved follow-up actions.
create-issue
Transform feature descriptions, bug reports, or improvement ideas into well-structured GitHub issues.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.