workflow

A step-by-step process for handling software work, from clarifying an idea through planning, coding, testing, review, and release.

In plain words
What is it for?
It helps define acceptance criteria, understand affected code, implement changes in small steps, run real tests, review the result, and prepare a release.
Why use it?
It prevents important work from being skipped or rushed during a non-trivial change. TDD, or test-driven development, means writing a failing test before the code that makes it pass.

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/hecer/yoke/workflow
Any agent
npx skills add HECer/yoke --skill workflow
Clone the repo
git clone --depth 1 https://github.com/HECer/yoke

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 323 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 $0.00028 $0.00323
Opus 5 $0.00014 $0.00161
Sonnet 5 $0.00006 $0.00065
Haiku 4.5 $0.00003 $0.00032

Measured yesterday against content hash 3fbddb012ab1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

canon/skills/workflow/SKILL.md · 23 lines

What it actually says

Workflow — the default order of operations

For any non-trivial change, move through these phases in order (skip only what genuinely does not apply):

When .yoke/config.yaml exists and the user wants Yoke to own planning plus autonomous execution, use yoke-workflow as the entrypoint. It adds the approved-plan → PRD → loop handoff and the configured critical-decision behavior to the phases below.

  1. Brainstorm the idea into a clear design — see brainstorming.
  2. Plan a concrete, testable implementation — see writing-plans.
  3. Understand the code — map the blast radius with the code-graph before changing anything.
  4. Implement test-first — RED → GREEN → REFACTOR, smallest steps — see tdd and minimal-code.
  5. Verify — run the real tests and exercise the change; never trust "it should work" — see verification-before-completion.
  6. Review — get an independent review of the diff before landing — see review / requesting-code-review.
  7. Ship — bump version, update changelog and docs, open the PR — see ship / document-release.

Stop-the-Line applies throughout: no implementation before acceptance criteria exist. Always prefer the least code that solves the task (minimal-code).

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. yesterday First seen · 23 lines · 28 tokens per session scan A 3fbddb012ab1

Subscribe to this mod's changes

workflow is a skill published in the GitHub repository HECer/yoke (2 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 323 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 2026-08-31.