quality-rubric

quality-rubric is a skill for Claude Code from Ohswedd/praxis. It costs 121 tokens per session (3,068 once invoked), scanned A, original, MIT.

A structured review process for checking a code change before it is considered complete. It uses several focused reviewers to examine issues such as security, regressions, duplication, and other quality concerns.

In plain words
What is it for?
Use it after non-trivial edits, when a stop gate reports an unreviewed change, or when you need a code review, audit, or quality check.
Why use it?
It provides a repeatable quality gate for meaningful changes instead of relying on an informal final check.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the praxis plugin — 15 skills, 8 commands, 13 agents, 5 hooks shipped together

Good fit Use it after non-trivial edits, when a stop gate reports an unreviewed change, or when you need a code review, audit, or quality check.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Ohswedd/praxis
Claude Code
/plugin install praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 15 skills, 8 commands, 13 agents, 5 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for quality-rubric

README.md
[![agentmods](https://agentmods.dev/badge/skills/ohswedd/praxis/quality-rubric/github.svg)](https://agentmods.dev/skills/ohswedd/praxis/quality-rubric)
Your own site
<a href="https://agentmods.dev/skills/ohswedd/praxis/quality-rubric"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/quality-rubric/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for quality-rubric

Your own site · 80×15
<a href="https://agentmods.dev/skills/ohswedd/praxis/quality-rubric"><img src="https://agentmods.dev/badge/skills/ohswedd/praxis/quality-rubric.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,068 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00121 $0.03068
Opus 5 $0.00060 $0.01534
Sonnet 5 $0.00024 $0.00614
Haiku 4.5 $0.00012 $0.00307

Measured 8d ago against content hash 6aa4f6078304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

quality-rubric 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 8d 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.

plugins/praxis/skills/quality-rubric/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Rubric

This skill is praxis's review engine. It turns "did we check everything?" from a per-prompt checklist into a repeatable, gated workflow. Invoke it via /praxis:audit or automatically after meaningful code changes.

Prefer maximum thoroughness: run high effort, and do not shortcut the vertical passes. Quality is the priority over speed.

Step 1: Scope the change (the branch, not the working tree)

A change does not stop being a change by being committed. Scope it as everything this branch has done since it left its base, plus whatever is still uncommitted:

python3 "${CLAUDE_PLUGIN_ROOT}/scripts/scope.py"     # base, commits, files, stats

That prints the review base and the exact commands for the diff. Use them:

  • git diff <base>...HEAD for what the branch has already committed, and git log <base>..HEAD for the commits themselves. Reviewing commit by commit is often faster than one large diff, and it shows the order the work was done in, which is where an accidental revert or a fix-up of a bug this same branch introduced becomes obvious.
  • git diff and git diff --staged for what is not committed yet.
  • Untracked files: they are part of the change and appear in no diff at all.

Never scope a review with git diff alone. On a branch that has committed anything, it is empty, and every auditor then reviews nothing and reports PASS. Praxis's own helpers (changed_files, the scanners, the change signature, the Stop gate) all use the branch scope, so a review that used the working tree alone would be narrower than the gate that judges it.

Then map the blast radius: callers, callees, shared state, public contracts, tests, and docs affected by the change.

Pass the scope into every dispatch. The auditors are read-only (Read, Grep, Glob) and have no shell, so they cannot run scope.py or git themselves: the base is a fact you hand them, not one they can discover. Every auditor prompt must state the base commit, the commits on the branch, and the files under review. An auditor told only "review the staged change" will read the working tree, find nothing on a branch that has committed its work, and return PASS. If you cannot resolve a base, say so in the prompt so the auditor reports the gap instead of reporting clean.

Read the full file on GitHub · 232 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. 8d ago First seen · 232 lines · 121 tokens per session scan A 6aa4f6078304

Subscribe to this mod's changes

quality-rubric is a skill published in the GitHub repository Ohswedd/praxis (1 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 3,068 once invoked, about $0.0006 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

scroll-craft

Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…

nateherkai/scroll-craft · 177 tokens

dream

Prunes and consolidates the project's auto-memory to keep it minimal — deletes stale, wrong, or redundant memories, merges overlapping ones into existing files, and trims the index. Strong bias against growth: never creates new memory files and never stores new facts. Verifies staleness against the current codebase…

oprogramadorreal/optimus-claude · 85 tokens

masterplan-detect

Suggest /masterplan import only when legacy masterplan bundle state files (docs/masterplan/ /state.yml at schema 5.x) exist without a matching v8 run. Generic planning artifacts (PLAN.md, TODO.md, ROADMAP.md, design docs, PR task lists) are NOT importable — no /masterplan import can ingest them; mention them only as…

rasatpetabit/masterplan · 116 tokens

foreman

Run a website build as the brain agent. Interview the user, force the scope and design decisions they would otherwise skip, lock a visual system, write one high-quality build brief, then either build it in this session or hand it to a coding agent (Codex, Claude Code, or any harness), and verify and ship it live. Use…

Turki-Sh/Foreman · 204 tokens

skill-creator

Authors and audits Claude Code skills: frontmatter, directory layout, scope, invocation control, and bundled references or scripts.

anilcancakir/claude-code · 28 tokens

git-master

Git expert: atomic commits with style detection, rebase and squash, and history archaeology through blame, bisect and pickaxe.

anilcancakir/claude-code · 29 tokens