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/rohirik/claude-code-config/workflowguidenpx skills add RohiRIK/claude-code-config --skill workflowguidegit clone --depth 1 https://github.com/RohiRIK/claude-code-configWhat 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 | $0.00060 | $0.01082 |
| Opus 5 | $0.00030 | $0.00541 |
| Sonnet 5 | $0.00012 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
WorkflowGuide 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Guide
Quick reference for picking the right path. Full detail: docs/workflow-daily.md · docs/workflow-dev.md
Which path?
Do you know exactly what to build? → Layer 2 (/spec)
Figuring it out or moving fast? → Layer 1 (/plan)
| Situation | Layer |
|---|---|
| Trivial one-liner | Just implement — no commands needed |
| Bug fix | Layer 1: /test (ProveIt) → /simplify → /capture → /verify → /commit-push-pr |
| Small feature (clear scope) | Layer 1: /plan → /build → /simplify → /capture → /verify → /commit-push-pr |
| Non-trivial feature | Layer 2: /spec → /plan → /dev → /test → /simplify → /capture → /verify → /commit-push-pr |
Layer 1 — Daily Workflow
Entry: /plan. You have a task and want to move.
[observe auto-fires] → /plan → IMPLEMENT (auto-accept: Shift+Tab×2) → /capture → /simplify → /verify → /commit-push-pr
[observe]is automatic — PrePlan hook fires when/planis typed, injecting git state + topic-scoped LTM recalls- After
/planconfirms → switch to auto-accept mode (Shift+Tab×2) for implementation /testreplaces the whole chain for bug fixes (ProveIt: write failing test → fix → pass)
Layer 2 — Dev Workflow
Entry: /spec (or /test for bugs). You know what to build and want it spec-driven.
/spec → /plan → /build (or /dev) → /test → /simplify → /capture → /verify → /commit-push-pr
/spec— recalls LTM + explores codebase → writes grounded spec with testable criteria/plan— each task maps to one acceptance criterion from the spec/build= task-by-task manual control ·/dev= full automation/test— final regression sweep across all changed files
Every Path Ends The Same Way
| Step | Command | What it does |
|---|---|---|
| Remove complexity | /simplify |
code-simplifier agent — flattens nesting, removes abstraction |
| Lock in context | /capture |
saves progress + fires /learn in one shot |
| Gate before ship | /verify |
tsc → lint → tests → build → security → diff |
| Ship | /commit-push-pr |
conventional commit → push → PR |
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 · 103 lines · 60 tokens per session scan A 4a2640042fb4
WorkflowGuide is a skill published in the GitHub repository RohiRIK/claude-code-config (10 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,082 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 2026-08-31.
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.