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/m2ux/workflow-server/workflow-canonnpx skills add m2ux/workflow-server --skill workflow-canongit clone --depth 1 https://github.com/m2ux/workflow-serverWhat 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 | $0.00127 | $0.02954 |
| Opus 5 | $0.00063 | $0.01477 |
| Sonnet 5 | $0.00025 | $0.00591 |
| Haiku 4.5 | $0.00013 | $0.00295 |
Grade A, and why
workflow-canon 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 yesterday.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Canon
The canon is four criteria homes plus a guard suite, all on disk in this repo.
This skill holds no criteria of its own. It locates the homes, enumerates their units, walks them, and reports. Copying Detect or stance text into this file would create a second home that drifts from the first — the defect the catalog itself names as canon-layer-cites-not-restates and no-duplicated-guidance. Cite entries by their kebab-case name; never by a bare AP-XX number and never by any count of the catalog's entries.
Homes
Locate the checkout first. Every path below is relative to the workflow-server repo root. When the cwd is inside the checkout, git rev-parse --show-toplevel gives it. When the session is rooted in a cursor workspace instead — a directory holding .mcp.json and a *.code-workspace but no workflows/ — the checkout is the project folder that *.code-workspace names, and it is an additional working directory of the session.
Confirm the resolved root holds workflows/workflow-design/resources/ before reading anything. workflows/ is a git submodule, so a shallow checkout may not have it; if the canon files are absent, say so rather than auditing from memory.
| Home | Path | Owns |
|---|---|---|
| Design Principles | workflows/workflow-design/resources/design-principles.md |
Prefer / before / only after stance. One unit per ## section. |
| Anti-Patterns | workflows/workflow-design/resources/anti-patterns.md |
Specific smells as Detect / Do not flag / Fix. One unit per ## family section. ~1700 lines — fetch by anchor. |
| Schema Construct Inventory | workflows/workflow-design/resources/schema-construct-inventory.md |
Informal-prose → formal-construct mappings. One unit per ## section. |
| Convention Conformance | workflows/workflow-design/resources/convention-conformance.md |
Comparison against sibling workflows. One unit. |
| Guard suite | scripts/guards.ts (registry) |
Mechanical checks. The registry is the enumeration — never maintain a parallel list. |
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.
- yesterday First seen · 123 lines · 127 tokens per session scan A d1e144693f12
workflow-canon is a skill published in the GitHub repository m2ux/workflow-server (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 127 tokens to every session and 2,954 once invoked, about $0.0006 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.