Borrowing it
Nothing to install: this file belongs to radiantlogicinc/fastworkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radiantlogicinc/fastworkflow/main/.claude/skills/fastworkflow-architecture-contract/SKILL.mdgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote 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.
[](https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-architecture-contract)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-architecture-contract"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-architecture-contract.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00217 | $0.07032 |
| Opus 5 | $0.00109 | $0.03516 |
| Sonnet 5 | $0.00043 | $0.01406 |
| Haiku 4.5 | $0.00022 | $0.00703 |
Grade A, and why
fastworkflow-architecture-contract 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 8d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastWorkflow Architecture Contract
The design decisions that must survive any refactor, the invariants the code assumes (some enforced, some merely assumed — labeled), and the known-weak points, each with file:line evidence. Facts verified 2026-07-09 against v2.22.2 (commit c33b9a5).
When to use / when NOT to use
| Situation | Skill |
|---|---|
| Changing core runtime code; reviewing a PR that touches WEC/ChatSession/turns; "why is it built this way?" | THIS skill |
| A runtime/build/train failure to triage right now | fastworkflow-debugging-playbook |
| Historical investigations, reverts, dead ends | fastworkflow-failure-archaeology |
| Intent-model internals, thresholds, DSPy signatures | fastworkflow-nlu-pipeline-reference |
| Env vars and CLI flags | fastworkflow-config-and-flags |
| Running the CLI / FastAPI server, artifact locations | fastworkflow-run-and-operate |
| What change classes are gated and why | fastworkflow-change-control |
| tau-bench / tau2 mechanics and the reliability campaign | fastworkflow-taubench-reference, tau2-reliability-campaign |
Vocabulary (defined once)
| Term | Meaning |
|---|---|
| WEC | WorkflowExecutionContext (fastworkflow/workflow_execution_context.py) — the transport-free, synchronous execution core. One per session. |
| ChatSession | CLI/REPL wrapper that composes a WEC and adds Queues + a daemon ChatWorker thread (fastworkflow/chat_session.py:27-48). |
| Topology A | ChatSession mode: ask_user blocks a worker thread on user_message_queue.get() until a human answers (workflow_agent.py:354-385). |
| Topology B | WEC mode (FastAPI, embedders): no queues; ask_user suspends the agent trajectory in memory and the call returns; the next message resumes it. |
| CME | The command metadata extraction internal workflow at fastworkflow/_workflows/command_metadata_extraction/ — a real fastWorkflow workflow that IS the NLU pipeline. |
| wildcard | The pseudo-command _workflows/command_metadata_extraction/_commands/wildcard.py whose single ResponseGenerator runs intent detection + parameter extraction. |
| Logical turn | One user interaction end-to-end, across any number of ask_user suspensions. One turn = one turn_key = one record (turn.py:240-247). |
| Embedder | Any host that owns a WEC's lifecycle (FastAPI server, ChatSession, a future Slack bot). |
| DSPy ReAct loop | The forked reason/act agent loop in fastworkflow/utils/react.py (fastWorkflowReAct), a vendored modification of DSPy's ReAct. |
| [A#] / [R#] / [X#] / Topic-n | Traceability tags into the TurnResult docs: design-doc Amendment / adversarial-review finding / architecture-review finding / feedback-session topic (docs/turn_result_design*.md; process in fastworkflow-change-control). |
What ships with it
2 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.
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.
- 8d ago First seen · 330 lines · 217 tokens per session scan A 55ab590be6e5
fastworkflow-architecture-contract is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 217 tokens to every session and 7,032 once invoked, about $0.0011 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.
Other skills, from other repositories
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.