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/codex-workflows/recipe-implementnpx skills add shinpr/codex-workflows --skill recipe-implementgit clone --depth 1 https://github.com/shinpr/codex-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 | $0.00018 | $0.00834 |
| Opus 5 | $0.00009 | $0.00417 |
| Sonnet 5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00083 |
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
subagents-orchestration-guide— agent coordination and workflow flows - [LOAD IF NOT ACTIVE]
documentation-criteria— scale-selected document path - [LOAD IF NOT ACTIVE]
requirement-convergence— outcome, exclusion, and rough-cost convergence before design - [LOAD IF NOT ACTIVE]
llm-friendly-context— cross-agent handoffs and task carrier
Spawn rule: every spawn_agent call uses fork_turns="none" so the subagent receives only the task message and explicitly provided context.
Full-Cycle Implementation
$ARGUMENTS
Orchestrator Definition
Core Identity: Coordinate the lifecycle, complete lightweight workflow operations directly, and invoke named specialists for their domain work.
Follow the scale-selected flow and its user approval points from subagents-orchestration-guide.
Step 1: Requirement Analysis
Spawn requirement-analyzer for compact request signals, scope evidence, cost evidence, affected-layer evidence, and decision-changing questions.
At the requirements stop, the orchestrator applies subagents-orchestration-guide Requirement Convergence from the user's wording and supplied evidence, resolves material questions, determines Structural Scale and affected layers, and selects the canonical route.
[STOP — BLOCKING] Present the converged requirement record, scale, affectedLayers, and scope to the user for confirmation. CANNOT proceed until user explicitly confirms.
Step 2: Canonical Workflow Routing
Apply the subagents-orchestration-guide Basic Flow for Work Planning using scale as the primary route. Use affectedLayers only to select the layer-specific additions and agents within that route:
| affectedLayers | Layer-specific routing |
|---|---|
["backend"] only |
Backend agents |
["frontend"] only |
UI Spec when required by the canonical flow, then frontend designer, executor, and quality fixer |
["backend", "frontend"] |
Fullstack monorepo flow with layer-specific analysis, design, and task routing |
What ships with it
1 file 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.
- 2d ago First seen · 72 lines · 18 tokens per session scan A 80e095e66739
recipe-implement is a skill published in the GitHub repository shinpr/codex-workflows (38 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 834 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
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
powerpoint
Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.
new-app
Scaffold a new Atomic Agents project from scratch — create the directory, pyproject.toml, env file, first agent, and a runnable entry point. Use when the user asks to start a new atomic-agents project from scratch, says "scaffold" / "new project" / "start from zero", or runs /atomic-agents:new-app.