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/shinpr/claude-code-workflows/recipe-implementnpx skills add shinpr/claude-code-workflows --skill recipe-implementgit clone --depth 1 https://github.com/shinpr/claude-code-workflowsWhat 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 | $0.00015 | $0.02043 |
| Opus 5 | $0.00008 | $0.01022 |
| Sonnet 5 | $0.00003 | $0.00409 |
| Haiku 4.5 | $0.00002 | $0.00204 |
Grade A, and why
recipe-implement 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explicit User Instruction: The user explicitly instructs and authorizes every subagent call named in this recipe. Execute each applicable call when its prerequisites are met.
Execute Skill: llm-friendly-context before writing Agent prompts, handoffs, or generated artifacts. Execute Skill: subagents-orchestration-guide before making workflow decisions, invoking agents, or resolving findings.
Context: Full-cycle implementation management (Requirements Analysis → Design → Planning → Implementation → Quality Assurance)
Orchestrator Definition
Core Identity: "I am an orchestrator." (see subagents-orchestration-guide skill)
Local authority gate: Make this recipe's workflow decisions and validate each returned result directly; delegate semantic deliverable production to the named specialist.
Review Resolution Gate [MANDATORY]: Resolve every actionable deliverable-review finding through subagents-orchestration-guide Review Resolution before correction or progression.
Before the first finding disposition, read references/review-resolution.md from the loaded subagents-orchestration-guide skill.
Execution Protocol:
- Invoke named specialists for deliverable production — pass deliverable paths between them and validate their results (see subagents-orchestration-guide "Orchestrator Execution Boundary")
- Follow subagents-orchestration-guide skill flows exactly:
- Execute one step at a time in the defined flow (Large/Medium/Small scale)
- When flow specifies "Execute document-reviewer" → Execute it immediately
- Stop at every
[Stop: ...]marker → Use AskUserQuestion for confirmation and wait for approval before proceeding
- Enter autonomous mode after confirmed Small requirements or Medium/Large batch approval
At each Agent invocation below, build the prompt as a mechanical extraction: copy the named source values into the exact fields, apply only the declared serialization, then invoke immediately.
CRITICAL: Execute all steps, sub-agents, and stopping points defined in subagents-orchestration-guide skill flows.
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 · 151 lines · 15 tokens per session scan A fa90debdbcf4
recipe-implement is a skill published in the GitHub repository shinpr/claude-code-workflows (675 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 2,043 once invoked, about $0.0001 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
dynamic-workflows
Ultracode / Max-Parallel mode — dynamic workflows fan work out across tens–hundreds of adversarially-verified parallel subagents for large, decomposable jobs (codebase-wide audits, big migrations, cross-checked research). Opt-in; higher token spend.
agent-teams
Experimental Agent Teams orchestration — run CCGodMode agents as parallel teammates with SharedTaskList coordination (requires CLAUDECODEEXPERIMENTALAGENTTEAMS=1).
cost-efficiency
Smart Routing — the DEFAULT CCGodMode routing policy. Risk-based, minimal-agent paths that preserve required safety gates for the changed scope.
departments
Expanded department-based orchestration for large cross-domain CCGodMode work. Freezes ownership, handoffs, and write scopes before implementation.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
ring:dispatching-workflows
Executing a phased plan in rolling waves where each phase runs as one multi-agent workflow harness: the supervisor elaborates the phase into tasks against the real landed code, launches a workflow that implements with TDD and runs mandatory in-harness review plus an adversarial contrarian pass (and researchers when…