using-op

A set of operating rules for routing project work, following repository conventions, and proving results.

In plain words
What is it for?
Use it to start conversations, route tasks through the project's commands, inspect conventions, verify claims, and report tree changes.
Why use it?
It makes development decisions traceable by requiring a real code convention before edits, evidence for completion, and a Git status check after changes.

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/artttj/rapid-stack/using-op
Any agent
npx skills add artttj/rapid-stack --skill using-op
Clone the repo
git clone --depth 1 https://github.com/artttj/rapid-stack

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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 $0.00042 $0.00582
Opus 5 $0.00021 $0.00291
Sonnet 5 $0.00008 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured yesterday against content hash b5002d81541b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-op 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.

The scan reads SKILL.md. This mod also ships 2 executable files (lib/status_line.py, lib/test_status_line.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/op/skills/using-op/SKILL.md · 22 lines

How it starts

The opening of the file, as written. The whole thing — 22 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using op

Personal operator layer for solo project work. Commands: /op:go (front door), /op:spec → /op:plan → /op:build (the gate for features), /op:ship, /op:sync, /op:show, /op:release (daily ops). Deep disciplines come from the superpowers plugin, review and polish from rs; op adds the routing, the gate, the ops verbs, and these rules.

Non-negotiable rules

  • Iron law: before writing any code, quote one real convention from the target repo as file:line plus the line itself. No quote, no code. (quote-before-code, github.com/artttj/quote-before-code — 930 graded runs, 0/40 → 40/40 correctness.)
  • No "done" without proof from this turn: a command output, a screenshot path, or a live URL. Failing tests are reported as failing. Deep procedure: superpowers:verification-before-completion.
  • End-of-turn git status line: after any turn that changed a working tree, the last line of the turn is python3 "__OP_ROOT__/skills/using-op/lib/status_line.py" <repo> output. If __OP_ROOT__ appears unsubstituted, resolve the op install path from ~/.claude/plugins/installed_plugins.json first.
  • Read-only by default. "full co-pilot" arms reversible gated actions for this session: staging, committing, creating the working branch, pushing to an existing upstream. "disarm co-pilot" stands down. Never covered: production deploys, publishes, force-push, deletion, history rewrites — these confirm every time.
  • An echoed gate phrase must execute: when the user types a confirmation, run the gated action in the same turn. Repeating the phrase back without acting is a bug.
  • Decisions are short arrow-choices, never open questions, whenever the options are enumerable.
  • Before a heavy step (spec, plan, deep debug, big build), suggest raising effort (xhigh/max) or an ultracode workflow, then let the user decide.
  • Per-project ops live in .claude/op.json (see op:project-recipes). Missing key → discover, confirm as arrow-choice, cache. Failing recipe command → rediscover and update. Never guess a deploy target.
  • Mirror the user's language (EN/RU). Command names, files, and commits stay English.
  • Every op command ends with its proof: what ran, what it produced, where to look.

Read the full file on GitHub · 22 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. yesterday First seen · 22 lines · 42 tokens per session scan A b5002d81541b

Subscribe to this mod's changes

using-op is a skill published in the GitHub repository artttj/rapid-stack (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 582 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.