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/ericboehs/claude-plugins/watch-slacknpx skills add ericboehs/claude-plugins --skill watch-slackgit clone --depth 1 https://github.com/ericboehs/claude-pluginsWhat 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 | $0.00006 | $0.00824 |
| Opus 5 | $0.00003 | $0.00412 |
| Sonnet 5 | $0.00001 | $0.00165 |
| Haiku 4.5 | $0.00001 | $0.00082 |
Grade A, and why
watch-slack 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
watch-slack
Surface Slack replies that are addressed to this Claude pane, so the user can
reply in the pane's :claude: notification thread to wake the agent.
How it works
- A single shared launchd service runs
slack-noti-listenuntargeted. It holds the one Slack Socket Mode connection and writes every #notifications message — pre-tagged with the pane it belongs to — to a shared log (~/.local/state/slack-noti/stream.log). - This skill arms a per-pane consumer (
watch-pane.sh) that tails that log and emits only the lines tagged for the current pane, re-resolving the pane's livesession:window.paneon every line so tmux window moves just work.
Why one shared listener: Slack delivers each Socket Mode event to only one connection sharing the app token. Running a listener per pane would make Slack round-robin events and starve panes. One socket, many local consumers.
Steps
1. Ensure the shared listener service is running
Run ${CLAUDE_PLUGIN_ROOT}/scripts/watch-slack-service.sh status. If it reports
(not loaded) or there is no log, run
${CLAUDE_PLUGIN_ROOT}/scripts/watch-slack-service.sh install to generate the
plist, bootstrap it, and start it. Confirm the log shows connected.
If CLAUDE_PLUGIN_ROOT is not set, resolve the scripts relative to this
SKILL.md (../../scripts/).
The listener needs BOEHS_SLACK_NOTI_SOCKET_XAPP (Socket Mode app token) and,
for pane-targeted threads, BOEHS_SLACK_NOTI_BOT_XOXB (bot token). The service
injects these via fnox exec when fnox is available. See the README for setup.
2. Arm the per-pane consumer with a persistent Monitor
Use the Monitor tool (persistent, long timeout) to run:
${CLAUDE_PLUGIN_ROOT}/scripts/watch-pane.sh
Each line the script emits is one event: a Slack reply addressed to this pane
(format [time] session:window.pane ⤷ who: text), or a socket reconnect/
disconnect notice. The script self-resolves the current pane from $TMUX_PANE,
so do not hardcode a pane id.
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 · 73 lines · 6 tokens per session scan A c1e42af87951
watch-slack is a skill published in the GitHub repository ericboehs/claude-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 6 tokens to every session and 824 once invoked, about $0.0000 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 2026-08-31.
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…