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-prepare-implementationnpx skills add shinpr/codex-workflows --skill recipe-prepare-implementationgit clone --depth 1 https://github.com/shinpr/codex-workflowsWrote 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/shinpr/codex-workflows/recipe-prepare-implementation)<a href="https://agentmods.dev/skills/shinpr/codex-workflows/recipe-prepare-implementation"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/recipe-prepare-implementation.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00024 | $0.00510 |
| Opus 5 | $0.00012 | $0.00255 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
recipe-prepare-implementation 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 4d 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 — 59 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— capability failure resolution and caller-return rules
Purpose
Run this optional side path when the user explicitly requests setup or Orchestrator Escalation Resolution identifies one concrete missing repository-local capability. Prepare existing repository-local tools needed to execute the approved Work Plan, then return a capability summary to the caller.
Work plan: $ARGUMENTS
Scope
Repository-local preparation includes existing project mechanisms for:
- dependency installation
- local containers or services
- repository-provided bootstrap commands
- test runner, browser harness, fixtures, and seed commands already referenced by the Work Plan or governing Design Doc
- non-secret local configuration derived from checked-in examples
Feature implementation, new product behavior, external account creation, credential acquisition, organizational approval, production access, deployment, and release execution remain in their owning workflows. The caller continues with the capabilities available after this side path.
Process
- Resolve the exact Work Plan path from
$ARGUMENTS, or from the build caller when invoked as its side path. - Read repository manifests, lockfiles, checked-in setup documentation, and scripts that control commands used by the Work Plan.
- Select the smallest existing setup commands that enable the planned repository checks.
- Execute those commands and capture their observable results.
- Classify each planned capability as
availableorunavailablewith concrete evidence. - Return the capability summary to the caller. In a build flow, unavailable capabilities become task-local verification limitations handled through Orchestrator Escalation Resolution. The approved Work Plan and its implementation task set remain unchanged.
Use the active execution plan when one exists. When setup has multiple dependent commands and no plan exists, create one and update it through completion.
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.
- 4d ago First seen · 59 lines · 24 tokens per session scan A 35b8f4d31aac
recipe-prepare-implementation is a skill published in the GitHub repository shinpr/codex-workflows (38 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 510 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.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…