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 skills add shinpr/codex-workflows --skill implementation-approachgit 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/implementation-approach)<a href="https://agentmods.dev/skills/shinpr/codex-workflows/implementation-approach"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/implementation-approach/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shinpr/codex-workflows/implementation-approach"><img src="https://agentmods.dev/badge/skills/shinpr/codex-workflows/implementation-approach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00022 | $0.00632 |
| Opus 5.5 | $0.00009 | $0.00253 |
| Sonnet 5.5 | $0.00004 | $0.00126 |
| Haiku 4.5 | $0.00002 | $0.00063 |
Grade A, and why
implementation-approach 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 5d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Approach
Strategy Selection
Use this sequence when a design or task needs an implementation approach:
- Current evidence — inspect the relevant responsibility, data/control path, representative repository pattern, and constraints that can change the choice.
- Direct MVP — identify the simplest complete path to the user's required result, including no change or removing unnecessary behavior when sufficient. A previously passed design is a revisable starting point.
- Necessity before detail — establish a concrete required result that this path cannot deliver before designing an extra mechanism. Discovery of a concern or a potential consumer supplies a candidate, not new requirements.
- Selection — consider subtraction and existing behavior first. Adopt an addition only when those cannot satisfy the requirement and its supported benefit justifies total UX, runtime, implementation, testing, documentation, and maintenance cost. Evidence alone does not select it.
- Detail and stop — define contracts, states, error handling, and proof only for the selected mechanisms. Stop when the required result and sufficient verification are executable; further technically valid possibilities remain unadopted.
Possible future reuse, generic best practice, speculative edge cases, and optional hardening are not failed items. A path or file count is supporting evidence, not a scale or strategy rule.
Keep this analysis in the active execution context. In an existing design rationale or handoff, retain only the decision-changing reason a material addition is needed over the direct path. Evaluate its layers, states, outputs, and tests together as one mechanism. Ordinary local choices need no separate record or alternative inventory.
Slicing Choice
Choose the smallest slicing structure that preserves dependency order and yields observable progress:
- Vertical — one user- or consumer-visible outcome can be completed across its layers without first creating a shared foundation.
- Foundation-first — multiple required outcomes depend on the same contract or mechanism that must exist before any can work.
- Hybrid — one verified shared dependency comes first, followed by outcome-oriented slices.
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.
- 5d ago Changed 34bb0b2c7f38
- 1mo ago Changed 842583be6b47
- 1mo ago First seen · 48 lines · 22 tokens per session scan A 25801e241209
implementation-approach is a skill published in the GitHub repository shinpr/codex-workflows (39 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 632 once invoked, about $0.0001 per session on Opus 5.5. 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.
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.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
ax-go-flow
Use when writing Go code with github.com/ax-llm/ax/packages/go for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
notifications
Send notifications through the unified notification router.