ss-coding-workflow

An end-to-end workflow that takes a ready plan or clear change request through branching, multi-agent coding, review, and pull-request or commit delivery.

In plain words
What is it for?
Use it for a complete, well-scoped change when you want the workflow to create a branch, coordinate coding agents, handle review feedback, and deliver the result.
Why use it?
It connects the separate development steps so a prepared task can move from implementation to delivery with review included.

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/lbk-open/super-spec/ss-coding-workflow
Any agent
npx skills add lbk-open/super-spec --skill ss-coding-workflow
Clone the repo
git clone --depth 1 https://github.com/lbk-open/super-spec

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,394 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 $0.00072 $0.03394
Opus 5 $0.00036 $0.01697
Sonnet 5 $0.00014 $0.00679
Haiku 4.5 $0.00007 $0.00339

Measured yesterday against content hash fcc2b38ee0bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ss-coding-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.

skills/ss-coding-workflow/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Coding Workflow

Chains the existing ss-* skills into a single execute-and-deliver flow:

ss-create-branch → ss-coding (built-in review) → review-acceptance loop → ss-create-pr

Core principle: thin orchestration. This skill never writes code itself. It calls the other skills in order, passes outputs along, and reports progress.

Review is not run twice. ss-coding already enforces a post-coding review internally and returns a verdict. This workflow never invokes ss-code-review separately — the review-acceptance loop below is driven entirely by that verdict.

Unlike ss-feature-workflow, there is no proposal or planning step here, and no manual gate by default — the input is either an already-prepared plan or a change instruction handed straight to coding.

When to Run

This is end-to-end orchestration: it creates a branch, spawns coding agents, runs reviews, and delivers the result. Only run it when the user explicitly asks for this skill or clearly wants the full execute-to-delivery pipeline. For an ordinary edit, a question, or a single-step request, do the work directly (or point to the one relevant ss-* skill).

Inputs

  • Execution input, one of:
    • a path to an existing execution plan (produced by ss-plan), or
    • a plain-language change instruction (e.g., "extract OrderService's helper methods into OrderUtils"). If ambiguous which one it is, ask; when deciding autonomously, treat text with a recognizable task/file structure as a plan, otherwise as a change instruction.
  • Delivery modefull (default) or lite. See "Delivery Mode" below.
  • Explicit branch name (optional) — used verbatim by ss-create-branch, skipping name derivation. Set this when a caller (such as ss-multi-repo-workflow) needs one unified branch name across repositories.
  • Skip-gates / decide-autonomously — kept for consistency with the other workflows; this workflow has no gate by default, so skip-gates has little effect here.
  • Worktree preference — forwarded to ss-create-branch.

Read the full file on GitHub · 228 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. yesterday First seen · 228 lines · 72 tokens per session scan A fcc2b38ee0bc

Subscribe to this mod's changes

ss-coding-workflow is a skill published in the GitHub repository lbk-open/super-spec (1 stars, last pushed 10d ago), licensed Apache-2.0. It adds 72 tokens to every session and 3,394 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 2026-08-31.