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/noisy/noisy-coding/local-dev-setupnpx skills add noisy/noisy-coding --skill local-dev-setupgit clone --depth 1 https://github.com/noisy/noisy-codingWhat 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 | $0.00077 | $0.00757 |
| Opus 5 | $0.00039 | $0.00378 |
| Sonnet 5 | $0.00015 | $0.00151 |
| Haiku 4.5 | $0.00008 | $0.00076 |
Grade A, and why
local-dev-setup scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
from this checkout. Verify: `curl -s http://127.0.0.1:7765/status` returns How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local dev environment for noisy-coding contributors
This skill lives in .claude/skills/ — project scope, for people hacking on
THIS repo. It is deliberately NOT in the plugin's skills/ directory, so it
never ships to end users.
The full recipe with rationale is docs/local-development.md — read it when
anything here surprises you. Quick path:
1. Dev daemon (port 7765; production keeps 8765–8767)
scripts/dev_daemon.sh
Builds the dashboard if dashboard/dist is missing, then starts the listener
from this checkout. Verify: curl -s http://127.0.0.1:7765/status returns
JSON. Dashboard: http://127.0.0.1:7765 — amber logo + LOCAL DEV badge.
Run it in the background (run_in_background) and restart it after changing
Python code; rebuild (cd dashboard && npm run build) after dashboard changes.
2. Session wiring — should already be in place
-
MCP is per contributor machine (LOCAL scope — a committed
.mcp.jsonwould be auto-loaded by the plugin and leak the dev server to end users):claude mcp add noisy-coding-dev --scope local \ --env NOISY_CODING_LISTENER_PORT=7765 -- uv run noisy-coding-mcpTools appear as
mcp__noisy-coding-dev__*after a restart. -
Hooks are committed to this repo, so normally there is nothing to do:
.claude/settings.json→ the five hooks duplicated with local commands (NOISY_CODING_LISTENER_PORT=7765 python3 hooks/<script>.py). They run IN ADDITION to the global production hooks — that is intended; each set talks to its own daemon.
If either is missing, restore it from docs/local-development.md §2.
Verify against the DAEMON, not just Vite
Vite serves public/ and its own module graph, masking daemon-side
gaps: the avatars sprite worked on :5173 for hours while the container
404'd it (the daemon's static route didn't know the file). Any change
involving static files, routes or daemon-served behavior must be checked
on the daemon port (7765 dev / 8765 prod build) — ideally with a
headless-Chrome screenshot — before calling it done.
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 · 65 lines · 77 tokens per session scan A 446c89ad728c
local-dev-setup is a skill published in the GitHub repository noisy/noisy-coding (6 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 757 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
postai-automation
Use when automating TikTok and Instagram video creation from product images using POST AI — generates dozens of captioned, voiced-over variants for affiliate and e-commerce marketing.
start-talking
Start and run an explicit, interactive Cadence Code conversation with Codex or Antigravity using fully local speech input and output. Use only when the user explicitly invokes $start-talking, /start-talking, or asks to start talking with Cadence Code.
jump-in
Interrupt an active Cadence Code conversation and add fresh spoken guidance to the current Codex or Antigravity task. Use only when the user explicitly invokes $jump-in or /jump-in after stopping the current host turn.
voice-settings
Choose Cadence Code's local speech and transcription models from the Codex or Antigravity UI. Use only when the user explicitly invokes $voice-settings, /voice-settings, or asks to open Cadence Code settings.
wrap-up
End an active Cadence Code conversation cleanly and release its local speech models. Use only when the user explicitly invokes $wrap-up, /wrap-up, or asks to wrap up the voice conversation.
speech-expert
Expert guide for speech-mcp - TTS, local/streaming STT, barge-in, wake word, voice command bus, and provider selection.