savecraft.gg: Skill for Claude Code

.claude/skills/working-on-daemon/SKILL.md

working-on-daemon is a skill for Claude Code from joshsymonds/savecraft.gg. It costs 65 tokens per session (1,225 once invoked), scanned A, original, Apache-2.0.

A set of project rules for developing Savecraft’s Go background service, which watches files and communicates with the server.

In plain words
What is it for?
Use it when changing daemon code, filesystem watching, plugin execution, WebSocket communication, push handling, or daemon tests.
Why use it?
It keeps daemon changes consistent with the project’s architecture, especially how the service connects, sends data, and handles linking.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is joshsymonds/savecraft.gg's own configuration. It tells Claude Code how to work on savecraft.gg itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything savecraft.gg configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshsymonds/savecraft.gg. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joshsymonds/savecraft.gg/main/.claude/skills/working-on-daemon/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joshsymonds/savecraft.gg

Made for: Claude Code.

Wrote 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.

agentmods badge for working-on-daemon

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-daemon/github.svg)](https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-daemon)
Your own site
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-daemon"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-daemon/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for working-on-daemon

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/working-on-daemon"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/working-on-daemon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,225 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01225
Opus 5 $0.00032 $0.00613
Sonnet 5 $0.00013 $0.00245
Haiku 4.5 $0.00006 $0.00122

Measured 9d ago against content hash a8683a239c91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

working-on-daemon 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 9d 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.

.claude/skills/working-on-daemon/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working on the Daemon

Read docs/daemon.md for the full architecture reference.

Daemon Lifecycle

Registration and linking are separate concerns:

  1. Register: Daemon connects to /ws/register, sends Register proto, receives RegisterResult (source_uuid, source_token, link_code), disconnects.
  2. Connect: Daemon immediately connects to /ws/source/{uuid} with Bearer auth. It is now online and can push saves, send events, receive config. The server silently drops pushes from unlinked sources (no user_uuid to store against), but the connection is live.
  3. Link (async): User enters the 6-digit link code at the web UI whenever they want. The server notifies the daemon over the existing WS connection. The daemon does NOT poll HTTP for link status.

Key principle: The daemon has exactly one network channel to the server — a single WebSocket connection. There are zero HTTP calls except downloading WASM plugin binaries from R2. Registration, save push, status, link notifications, config updates, link-code refresh, unlink, deregister — all flow over WS as proto messages.

All source management operations (link state, link-code refresh, unlink, deregister) flow over WS as proto messages. The daemon has zero HTTP calls to the server except downloading WASM plugin binaries from R2.

Verification

After changes, run in order:

just fmt-go        # goimports
just lint-go       # staticcheck + go vet
just test-go       # unit tests
just test-go-race  # race detector (before committing)

Interface Pattern

Every external dependency has an interface in internal/daemon/. Tests inject hand-written fakes. Real implementations live in separate packages and satisfy interfaces implicitly.

Interface Real impl Fake location
Watcher internal/watcher/ internal/daemon/daemon_test.go
Runner internal/runner/ internal/daemon/daemon_test.go
WSClient internal/wsconn/ internal/daemon/daemon_test.go
FS internal/osfs/ internal/daemon/daemon_test.go
PluginManager internal/pluginmgr/ internal/daemon/daemon_test.go

Read the full file on GitHub · 107 lines

Changes

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.

  1. 9d ago First seen · 107 lines · 65 tokens per session scan A a8683a239c91

Subscribe to this mod's changes

working-on-daemon is a skill published in the GitHub repository joshsymonds/savecraft.gg (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,225 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

golang-graphql

Implements GraphQL APIs in Golang using gqlgen or graphql-go. Apply when building GraphQL servers, designing schemas, writing resolvers, handling subscriptions, or integrating GraphQL with existing Go HTTP services. Also apply when the codebase imports github.com/99designs/gqlgen or github.com/graph-gophers/graphql-go.

samber/cc-skills-golang · 77 tokens

golang-pro

Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling. Use when building Go applications requiring concurrent programming…

Jeffallan/claude-skills · 95 tokens

golang-grpc

Provides gRPC usage guidelines, protobuf organization, and production-ready patterns for Golang microservices. Use when implementing, reviewing, or debugging gRPC servers/clients, writing proto files, setting up interceptors, handling gRPC errors with status codes, configuring TLS/mTLS, testing with bufconn, or…

samber/cc-skills-golang · 72 tokens

golang-swagger

Golang OpenAPI/Swagger documentation with swaggo/swag — annotation comments (@Summary, @Param, @Success, @Router, @Security), swag init code generation, framework integrations (gin, echo, fiber, chi, net/http), security definitions (Bearer/JWT, OAuth2, API key), and struct tags (swaggertype, enums, example…

samber/cc-skills-golang · 146 tokens

layered-architecture-types

Enforce primitive-at-edges / strong-types-in-Business layering and the toBus/fromBusResponse/toDB converter pattern. Use when writing, editing, or auditing Go files under app/, business/domain/, or .../stores/db.

ardanlabs/service · 56 tokens

printing-press

Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a…

mvanhorn/cli-printing-press · 86 tokens