software-development-workflow

A workflow for making software changes carefully, from understanding the request and existing code through focused edits and verification.

In plain words
What is it for?
Implementing, fixing, refactoring, testing, reviewing, or completing changes that involve more than a tiny mechanical edit.
Why use it?
It reduces the risk of solving the wrong problem, introducing unrelated changes, or claiming a fix without evidence that it works.

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/daaaaave/agentic-workspace-core/software-development-workflow
Any agent
npx skills add Daaaaave/agentic-workspace-core --skill software-development-workflow
Clone the repo
git clone --depth 1 https://github.com/Daaaaave/agentic-workspace-core

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,423 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 $0.00090 $0.01423
Opus 5 $0.00045 $0.00711
Sonnet 5 $0.00018 $0.00285
Haiku 4.5 $0.00009 $0.00142

Measured 2d ago against content hash 0864ce95e409, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

software-development-workflow 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.

payload/.agents/skills/software-development-workflow/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Software Development Workflow

Goal

Make coding agents behave like careful software engineers: define what is being changed, understand the existing system, make focused edits, debug from evidence, handle security risk explicitly, and only claim completion after verification.

Core Principle

Use the smallest workflow that can safely finish the task, but do not confuse the smallest workflow with the cheapest patch. For non-trivial or durable work, choose the best-fit solution for the task's risk, lifetime, and project architecture.

Do not load every reference by default. Load only the references/ files whose routing conditions match the current task.

This skill coordinates one software change from intent to evidence. It does not replace project knowledge, external research, skill authoring, or handoff skills; it calls or yields to them when their trigger is stronger.

Use When

  • The user asks to build, fix, refactor, test, review, or prepare code changes.
  • The task changes behavior, touches multiple files, or depends on project conventions.
  • A bug, failing test, broken build, runtime error, or unexpected behavior appears.
  • The work has security, privacy, compatibility, migration, public API, or release risk.
  • The agent is about to say a coding task is done.

Do Not Use When

  • The task is external/current research only; use research-to-knowledge.
  • The task is durable repository knowledge work only; use project-knowledge.
  • The task is creating, splitting, securing, or evaluating skills; use write-agent-skill.
  • The task is only a temporary handoff; use write-agent-handoff.
  • The task is a tiny local edit with obvious scope, no behavior change, and no need for workflow judgment.

Existing Skill Order

This skill does not replace the core starter skills.

  1. If the request changes skills, use write-agent-skill instead of this skill.
  2. If project conventions, architecture, workflows, decisions, domain terms, or known gotchas may matter, use project-knowledge before coding.
  3. If current external documentation, technology choice, dependency choice, or source-backed comparison may materially affect the implementation, use research-to-knowledge before coding.
  4. If the request needs transfer state, use write-agent-handoff after or instead of this skill.

Read the full file on GitHub · 93 lines

Files

What ships with it

6 files 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.

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. 2d ago First seen · 93 lines · 90 tokens per session scan A 0864ce95e409

Subscribe to this mod's changes

software-development-workflow is a skill published in the GitHub repository Daaaaave/agentic-workspace-core (6 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 1,423 once invoked, about $0.0005 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 2026-08-31.