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.
git clone --depth 1 https://github.com/fusengine/agentsWrote 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/commands/fusengine/agents/watch)<a href="https://agentmods.dev/commands/fusengine/agents/watch"><img src="https://agentmods.dev/badge/commands/fusengine/agents/watch/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/commands/fusengine/agents/watch"><img src="https://agentmods.dev/badge/commands/fusengine/agents/watch.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 | $0.00023 | $0.00473 |
| Opus 5.5 | $0.00009 | $0.00189 |
| Sonnet 5.5 | $0.00005 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
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 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.
What it actually says
Watch - Claude Code Update Tracker
Monitor Claude Code releases and verify plugin ecosystem compatibility.
Usage
/watch- Technical changelog scan + compatibility check/watch --pulse- Full scan + community sentiment analysis/watch --since 1.5.0- Check changes since specific version
Modes
Default Mode (Technical)
- Fetch latest changelog from code.claude.com
- Compare against known API surface (api-surface.md)
- Scan plugin files for impacted APIs
- Report with [BREAKING], [DEPRECATED], [NEW] tags
Pulse Mode (--pulse)
Everything in default mode, plus:
- Search community feedback via Exa web_search
- Analyze sentiment via Exa deep_researcher
- Gather real-world usage patterns
- Compare with competitor tools
Data Sources
| Source | Method | Mode |
|---|---|---|
| Changelog | WebFetch code.claude.com | Default |
| Docs index | WebFetch llms.txt | Default |
| Hook/Plugin API | Grep local files | Default |
| Community blogs | Exa web_search | --pulse |
| Deep analysis | Exa deep_researcher | --pulse |
| Code patterns | Exa get_code_context | --pulse |
Report Format
# Claude Code Update Report
Date: {date}
Latest Version: {version}
New Since Last Check: {count}
## [BREAKING] Changes
- {description} → Impact: {affected_files}
## [DEPRECATED] APIs
- {api} → Migration: {alternative}
## [NEW] Features
- {feature} → Opportunity: {how_to_leverage}
## [COMMUNITY] Pulse (--pulse only)
- Sentiment: {positive/neutral/negative}
- Key Topics: {list}
- Notable Feedback: {quotes_with_sources}
Arguments
$ARGUMENTSspecifies mode and version filter
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 · 70 lines · 23 tokens per session scan A c9f0e6cb6a49
watch is a command published in the GitHub repository fusengine/agents (33 stars, last pushed 9d ago), licensed MIT. It adds 23 tokens to every session and 473 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
techdebt
Find and report technical debt in the codebase.
bug
Report a bug instantly to the bug Inbox (append-only, any language, safe mid-work).
triage-bug
Turn bug Inbox reports into registered, prioritized bugs (separate from /triage).
audit
Audit a Next.js project for common issues, anti-patterns, and misconfigurations.
help
Rubber Duck: what it does, how to steer it, how to stop it.
fix-issue
Command "fix-issue" from KhaiTrang1995/claude-code-structure, covering /project:fix-issue – fix issue command, usage, description, shell steps and run tests after fix.