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/ergo-services/claude/frameworknpx skills add ergo-services/claude --skill frameworkgit clone --depth 1 https://github.com/ergo-services/claudeWhat 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 | $0.00072 | $0.01697 |
| Opus 5 | $0.00036 | $0.00848 |
| Sonnet 5 | $0.00014 | $0.00339 |
| Haiku 4.5 | $0.00007 | $0.00170 |
Grade A, and why
framework 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ergo Framework
Distributed, fault-tolerant actor-based systems in Go with Erlang-style reliability. This skill targets Ergo Framework v3.3+. It is organised as an index plus topic-focused reference files — load only what the current task needs.
When a signature or constant must be exact, verify at the source: $(go env GOMODCACHE)/ergo.services/ergo@<version>/ (gen/, act/, app/, meta/, net/edf/).
Reference Files
| Topic | File | When to read |
|---|---|---|
| Actor lifecycle, mailbox, HandleMessage/Call/Event, Link/Monitor/Alias, Events, CoreEvent bus | references/actors.md |
Implementing any actor |
| Supervisor types, restart strategies, intensity, Significant, KeepOrder, per-child restart, dynamic children | references/supervision.md |
Designing supervision trees |
| Send/Call, important delivery, priorities, compression, fallbacks, MessageOptions | references/messages.md |
Wiring messages between actors or nodes |
| Embed app.Application, Load(args), Init/Start/Stop lifecycle, ApplicationSpec, Depends, Tags, Map | references/application.md |
Building an application |
| Pool, act.Router (message routing), act.WebWorker, AddWorkers/RemoveWorkers, when NOT to use | references/pool.md |
High message load, routing, web handlers |
| TCPServer, TCPConnection, UDPServer, WebServer, Port, ProcessPool routing, meta limitations | references/meta.md |
I/O integration |
| NodeOptions, NetworkOptions, NetworkFlags defaults, Security, CertManager/TLS, Events, TargetManager | references/node.md |
Node configuration, security, TLS |
| gen.Log, LogLevel, structured fields, custom LoggerBehavior | references/logging.md |
Logging from actors, custom loggers |
| Tracing samplers, business spans (StartTracingSpan), exporters, TracingFlags | references/tracing.md |
Distributed tracing, custom spans |
| gen.Cron, CronJob, cron actions, MessageCron, fallbacks | references/cron.md |
Scheduled jobs |
| gen sentinels, TerminateReason*, gen.Errorf, matching with errors.Is | references/errors.md |
Matching errors and termination reasons |
| Network().RegisterType, schema evolution, ApplicationSpec.Network, visibility matrix | references/edf.md |
Cross-node message types |
| etcd vs Saturn, Registrar interface, ResolveApplication filters, Routes, proxy, NetworkFlags | references/cluster.md |
Distributed deployment |
| testing/unit (Spawn, Should*), testing/stage (multi-node), testing/check, testing/mock | references/testing.md |
Writing actor tests |
| actor/health (K8s probes), actor/leader (Raft election), actor/metrics (Prometheus) | references/actor-lib.md |
Operational actors |
| application/mcp (diagnostics), observer (web UI), pulse (OTLP), radar (bundle) | references/applications-lib.md |
Observability and diagnostics |
| meta/websocket, meta/sse | references/meta-lib.md |
WebSocket / SSE servers |
| registrar/etcd, registrar/saturn, logger/colored, logger/rotate, logger/sentry | references/integrations.md |
External service integrations |
| proto/erlang23 (EPMD, ETF, DIST) | references/erlang-protocol.md |
Interop with Erlang/OTP nodes |
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/actor-lib.md 14 KB
- references/actors.md 19 KB
- references/application.md 19 KB
- references/applications-lib.md 10 KB
- references/cluster.md 18 KB
- references/cron.md 12 KB
- references/edf.md 12 KB
- references/erlang-protocol.md 14 KB
- references/errors.md 13 KB
- references/integrations.md 14 KB
- references/logging.md 15 KB
- references/messages.md 11 KB
- references/meta-lib.md 11 KB
- references/meta.md 18 KB
- references/node.md 21 KB
- references/pool.md 23 KB
- references/supervision.md 15 KB
- references/testing.md 31 KB
- references/tracing.md 16 KB
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 · 89 lines · 72 tokens per session scan A ca7896605670
framework is a skill published in the GitHub repository ergo-services/claude (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,697 once invoked, about $0.0004 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.