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/sandraschi/speech-mcp/session-contextnpx skills add sandraschi/speech-mcp --skill session-contextgit clone --depth 1 https://github.com/sandraschi/speech-mcpWhat 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 | $0.00096 |
| Opus 5 | $0.00000 | $0.00048 |
| Sonnet 5 | $0.00000 | $0.00019 |
| Haiku 4.5 | $0.00000 | $0.00010 |
Grade A, and why
session-context 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 3d 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
Session Context (Speech MCP)
You have access to a multi-provider speech gateway with TTS, STT, wake word, RAG, and fleet voice command bus.
Before starting work:
- Check what providers are configured: tools list or provider status
- Search docs for relevant configuration: search_docs(query="")
At end of work:
- Persist any insights to the RAG knowledge base
- Log completed tasks for session continuity
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.
- 3d ago First seen · 12 lines · 0 tokens per session scan A d35f25fc8f80
session-context is a skill published in the GitHub repository sandraschi/speech-mcp (2 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 96 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 2026-08-31.
Other skills, from other repositories
ai-media
Use when a creative goal must become a finished media file: pick and order generative-media models per modality — AI voiceover, image-to-video clips, score — then glue them with ffmpeg (mux, duck, loudnorm, concat). NOT still-image generation/editing (that is replicate-images); NOT code-rendered React compositing…
after-production-release
What to tell the user right after publishing a noisy-coding release — derive the minimal refresh steps (image? plugin? per-session reloads?) from what actually changed and present them as a short spoken summary plus a bulleted console checklist. Use every time a release/tag is pushed, when the user asks "what do I…
creating-releases
How to cut a noisy-coding release — version bump, tag, GitHub release via gh, and above all HOW TO WRITE the release notes (agent-quotable Highlights, pain-first framing, upgrade notes derived from what changed). Repo-local skill for maintainers; use whenever asked to release, publish a version, or write release notes.
local-dev-setup
Set up or fix the side-by-side LOCAL DEV instance of noisy-coding in this repo — dev daemon on port 7765, noisy-coding-dev MCP, project-scoped hooks. Use when asked to prepare the local development environment, when the dev daemon is down, or when a session in this repo should talk to the dev instance instead of…
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.
character-matrix
How to interpret the noisy-coding Character Matrix — the four personality sliders (humor, honesty, brevity, chatty) set on the dashboard and delivered as [CHARACTER] instructions. Use whenever a [CHARACTER] instruction arrives, when speaking through the noisy-coding speak tool, or when the user asks about tuning your…