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 skills/minchenlee/c9watch/c9watch-clinpx skills add minchenlee/c9watch --skill c9watch-cligit clone --depth 1 https://github.com/minchenlee/c9watchWrote 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/minchenlee/c9watch/c9watch-cli)<a href="https://agentmods.dev/skills/minchenlee/c9watch/c9watch-cli"><img src="https://agentmods.dev/badge/skills/minchenlee/c9watch/c9watch-cli.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 | $0.00119 | $0.01320 |
| Opus 5 | $0.00060 | $0.00660 |
| Sonnet 5 | $0.00024 | $0.00264 |
| Haiku 4.5 | $0.00012 | $0.00132 |
Grade C, and why
c9watch-cli scanned grade C with 2 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 4d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/minchenlee/c9watch/main/install-cli.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/minchenlee/c9watch/main/install-cli.sh | bash How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
c9watch CLI
c9watch is a CLI tool that lets you monitor and manage all Claude Code sessions running on the machine. Every command outputs JSON. Use it to see what other sessions are doing, search past work, track costs, and coordinate with sibling agents.
Before you start
Verify c9watch is available:
which c9watch && c9watch --version
If not installed, tell the user:
c9watch CLI is not installed. Install it with:
curl -fsSL https://raw.githubusercontent.com/minchenlee/c9watch/main/install-cli.sh | bash
Commands reference
List active sessions
c9watch list # all sessions
c9watch list --compact # minimal fields (saves tokens)
c9watch list --project myapp # filter by project path
c9watch list --status NeedsAttention # filter by status
Status values: Working, WaitingForInput, NeedsAttention, Idle
Compact output fields: id, pid, status, projectPath, sessionName, pendingToolName
Full output adds: firstPrompt, messageCount, modified, customTitle, gitBranch, summary, latestMessage, pendingToolInput, taskProgress
Status overview
c9watch status # counts by status and project
c9watch status --project myapp # filtered
Returns total, byStatus, byProject, and needsPermission (sessions waiting for approval). This is the fastest way to answer "is anything stuck?" — check needsPermission first.
Identify yourself
c9watch self
Walks the PID tree to find the calling Claude Code process and returns your own session object. Use this to discover your own session ID, project path, git branch, or task progress without the user telling you.
View a conversation
c9watch view <session-id> # full conversation
c9watch view <session-id> --last 5 # last 5 messages (saves tokens)
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.
- 4d ago First seen · 141 lines · 119 tokens per session scan C 84ea4b923056
c9watch-cli is a skill published in the GitHub repository minchenlee/c9watch (127 stars, last pushed 17d ago), licensed MIT. It adds 119 tokens to every session and 1,320 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…