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/ambient-code/platform/grpc-devnpx skills add ambient-code/platform --skill grpc-devgit clone --depth 1 https://github.com/ambient-code/platformWhat 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 | $0.01027 |
| Opus 5 | $0.00000 | $0.00513 |
| Sonnet 5 | $0.00000 | $0.00205 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
grpc-dev 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: grpc-dev
Activates when: Working on gRPC streaming, AG-UI event flow, WatchSessionMessages, control plane ↔ runner protocol, or debugging gRPC connectivity.
Architecture
Runner Pod (Claude Code)
│ pushes AG-UI events via gRPC
▼
Control Plane (CP)
│ fan-out multiplexer — one runner, N watchers
▼
WatchSessionMessages RPC (streaming)
│
├── acpctl session messages -f
├── Go SDK session_watch.go
├── Python SDK _grpc_client.py
└── TUI dashboard (acpctl ambient)
Proto Definitions
Location: components/ambient-api-server/proto/ambient/v1/sessions.proto
Key RPC:
rpc WatchSessionMessages(WatchSessionMessagesRequest)
returns (stream SessionMessageEvent);
Generated stubs: pkg/api/grpc/ambient/v1/sessions_grpc.pb.go
Regen: cd components/ambient-api-server && make generate
AG-UI Event Types
| Event | Direction | Meaning |
|---|---|---|
RUN_STARTED |
runner → CP → client | Session began executing |
TEXT_MESSAGE_CONTENT |
runner → CP → client | Token chunk (streaming) |
TEXT_MESSAGE_END |
runner → CP → client | Message complete |
MESSAGES_SNAPSHOT |
runner → CP → client | Full message history |
RUN_FINISHED |
runner → CP → client | Session done (terminal event) |
RUN_FINISHED must be forwarded exactly once. CP must not duplicate or drop it.
Authentication
gRPC auth: pkg/middleware/bearer_token_grpc.go
Test token bypass: When a non-JWT token (e.g. test-user-token K8s secret) is used, the JWT username claim is absent from the gRPC context. The WatchSessionMessages handler MUST skip the per-user ownership check in this case:
username, ok := CallerUsernameFromContext(ctx)
if ok && username != session.Owner {
return status.Error(codes.PermissionDenied, "not session owner")
}
// If !ok (no username in context), allow — non-JWT token
Fan-Out Pattern
The CP maintains a subscriber map per session ID. When a new WatchSessionMessages client connects:
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 · 124 lines · 0 tokens per session scan A 2094f5c1f10d
grpc-dev is a skill published in the GitHub repository ambient-code/platform (129 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,027 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 2026-08-30.
Other skills, from other repositories
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
company-hiring-intelligence
Reverse-engineer what a company is building by scraping their job postings, careers page, LinkedIn Jobs, and engineering blog using TinyFish web agents. Use whenever a user wants to understand a company's strategic direction from hiring signals, do competitive intelligence, figure out a tech stack from job…
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.