stage

A plugin that generates multi-stage command-line AI development loops through conversation.

In plain words
What is it for?
Use it to build multi-stage `claude -p` loops.
Why use it?
The available description does not provide enough detail to say more about the problem it removes.

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/photostructure/coding-skills/stage
Any agent
npx skills add photostructure/coding-skills --skill stage
Clone the repo
git clone --depth 1 https://github.com/photostructure/coding-skills

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,453 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 $0.00037 $0.02453
Opus 5 $0.00018 $0.01226
Sonnet 5 $0.00007 $0.00491
Haiku 4.5 $0.00004 $0.00245

Measured 2d ago against content hash 321452a05d31, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stage 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/stage_hunks.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/coding/skills/stage/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage Session Changes

More on these workflows: photostructure.com/coding (no dedicated stage article yet)

Stage ONLY the changes that belong to the current body of work and compose a Conventional Commit message.

If, after checking the current git status, you find that all of your changes have been committed already, tell the user that: this skill is done.

NEVER git add an entire modified file unless every hunk in its diff belongs to this work.

Interactive staging may be unavailable. This skill includes scripts/stage_hunks.py for deterministic, non-interactive partial staging on Windows and POSIX hosts.

One concern per commit

If the session touched several distinct concerns, you MUST propose splitting them into separate commits — one per concern. We want small, focused, coherent commits in git history, not dogpiles and junk drawers.

Signs the session's work should be split:

  • Changes span unrelated features, bugs, or subsystems (e.g. a CSS tweak + an unrelated backend fix)
  • You'd need "and" in the commit subject to describe it (fix X and refactor Y)
  • The commit message would exceed 10 lines to explain everything
  • Some changes are refactors/cleanup while others are behavior changes
  • Tests for feature A are mixed with implementation of feature B

When splitting, run the full procedure below once per commit: inventory just that concern's files, stage them, compose a focused message, get approval, commit — then move on to the next concern. Do NOT stage everything at once and try to describe it in a single message.

When in doubt about whether changes belong together, ask the user which grouping they prefer before staging.

Gather live context

Run these commands at invocation time; never rely on embedded or previously captured output:

git status --short
git diff --cached --stat
git log --oneline -5

Procedure

1. Inventory Changes to Stage

Read the full file on GitHub · 222 lines

Files

What ships with it

2 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 · 222 lines · 37 tokens per session scan A 321452a05d31

Subscribe to this mod's changes

stage is a skill published in the GitHub repository photostructure/coding-skills (3 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 2,453 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

git-commit

Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

fvadicamo/dev-agent-skills · 49 tokens

commit

Stage, commit, push, open a PR, and merge to main. Use ONLY on explicit commit intent — user says "commit", "ship it", "push this", "open a PR", "merge to main", "let's commit this", or prefixes with /commit. Do NOT auto-invoke on vague end-of-task phrases ("we're done", "wrap up") — those require explicit…

pedrohcgs/claude-code-my-workflow · 105 tokens

git-commit

Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.

decebals/claude-code-java · 38 tokens

version-control

Manage Git repositories and collaborative workflows — branching strategies, commit hygiene, conflict resolution, pull requests, hooks, and .gitignore management. Use when the user requests version control or provides relevant inputs for this workflow.

seb1n/awesome-ai-agent-skills · 45 tokens

decision-records

Creates, supersedes and validates decision records (ADRs) against the convention a collection already follows, instead of imposing a published one. Use when the user wants to record a decision, write an ADR, supersede an existing decision, audit or lint a decisions folder, check that an ADR index is in sync, or asks…

fvadicamo/dev-agent-skills · 113 tokens

github-pr-review

Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…

fvadicamo/dev-agent-skills · 95 tokens