engineering-flow

engineering-flow is a skill for Claude Code, Codex from danicat/skills. It costs 76 tokens per session (1,203 once invoked), scanned A, original, Apache-2.0.

A set of software engineering guidelines for planning, designing, and reviewing code changes. It covers RFCs, which are proposals for discussion, and ADRs, which record final architecture decisions.

In plain words
What is it for?
Use it to structure technical proposals, record architecture choices, prioritize tasks, apply versioning rules, and maintain cleaner code.
Why use it?
It helps teams turn uncertain ideas into documented decisions and keep implementation work small, testable, and focused. It also calls out problems such as unclear errors, dead code, and unnecessary abstractions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/danicat/skills/engineering-flow
Any agent
npx skills add danicat/skills --skill engineering-flow
Clone the repo
git clone --depth 1 https://github.com/danicat/skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for engineering-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/danicat/skills/engineering-flow.svg)](https://agentmods.dev/skills/danicat/skills/engineering-flow)
Your own site
<a href="https://agentmods.dev/skills/danicat/skills/engineering-flow"><img src="https://agentmods.dev/badge/skills/danicat/skills/engineering-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,203 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00076 $0.01203
Opus 5 $0.00038 $0.00602
Sonnet 5 $0.00015 $0.00241
Haiku 4.5 $0.00008 $0.00120

Measured 3d ago against content hash efb5186721d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engineering-flow 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 3d 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.

coding/engineering-flow/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engineering Flow

Engineering standards, decision pipelines, and code hygiene rules.


Delivery Principles

Ship working software in small, verifiable increments:

  • Keep changes scoped to a single logical objective.
  • Avoid speculative abstractions and overengineering.
  • Implement thin, vertical slices from entrypoint to persistence.
  • Verify each slice with automated tests and compiler checks before proceeding.

Design Pipeline: RFCs and ADRs

Separate exploration from permanent architectural choices:

graph TD
    A[Ambiguous Goal / High Uncertainty] --> B[RFC in design/rfc/]
    B -->|Consensus Reached| C[ADR in design/adr/]
    C --> D[Implementation Tasks]
    E[Trivial / Low-Uncertainty Task] --> D
  • RFCs (design/rfc/): Use during exploration when requirements are ambiguous, trade-offs need debate, or multiple viable architectures exist. RFCs are fluid working documents.
  • ADRs (design/adr/): Use to record finalized decisions. ADRs are immutable historical logs capturing context, chosen architecture, and accepted trade-offs.
  • Tasks: Break ADR conclusions into concrete checklist items with clear acceptance criteria.

Task Prioritization

Categorize work by technical certainty and business value:

High Technical Certainty Low Technical Certainty
High Value Direct execution: Implement interactively with compiler feedback and tight test loops. Research & Spikes: Do not write production code yet. Run throwaway spikes in scratch/ or draft an RFC.
Low Value Delegate: Offload to background tasks or subagents. Defer / Discard: Drop or postpone until certainty increases or value is demonstrated.

Research & Evidence Hierarchy

Do not guess APIs, package syntax, or model behaviors. Ground technical decisions in primary sources:

[1] Source Code (highest authority)
  └── [2] Official Documentation & API Reference
        └── [3] Official Release Notes & Announcements
              └── [4] Industry Expert Articles (< 3 months old)
                    └── [5] Community Posts (< 3 months old)
                          └── [6] Stale Articles (> 3 months old — discard)
                                └── [7] Social Media (unverified — cross-check first)

Read the full file on GitHub · 125 lines

Changes

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.

  1. 3d ago First seen · 125 lines · 76 tokens per session scan A efb5186721d6

Subscribe to this mod's changes

engineering-flow is a skill published in the GitHub repository danicat/skills (16 stars, last pushed 4d ago), licensed Apache-2.0. It adds 76 tokens to every session and 1,203 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens