norma-workflow

norma-workflow is a skill for Claude Code, Codex from qualityclouds/norma-mcp. It costs 61 tokens per session (531 once invoked), scanned A, original, MIT.

A workflow that checks code against the rules for the detected technology stack and records each result in an audit trail. An audit trail is a history of what was checked and what happened.

In plain words
What is it for?
Preparing rules before coding, checking changed files, fixing failed checks, and recording which rules were followed.
Why use it?
It helps teams apply the same coding standards consistently and keep evidence that checks were performed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Preparing rules before coding, checking changed files, fixing failed checks, and recording which rules were followed.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qualityclouds/norma-mcp/norma-workflow
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.

Any agent
npx skills add qualityclouds/norma-mcp --skill norma-workflow
Clone the repo
git clone --depth 1 https://github.com/qualityclouds/norma-mcp

Made for: Claude Code, Codex.

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 norma-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/qualityclouds/norma-mcp/norma-workflow.svg)](https://agentmods.dev/skills/qualityclouds/norma-mcp/norma-workflow)
Your own site
<a href="https://agentmods.dev/skills/qualityclouds/norma-mcp/norma-workflow"><img src="https://agentmods.dev/badge/skills/qualityclouds/norma-mcp/norma-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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 $0.00061 $0.00531
Opus 5 $0.00030 $0.00266
Sonnet 5 $0.00012 $0.00106
Haiku 4.5 $0.00006 $0.00053

Measured 4d ago against content hash 06c172facc1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

norma-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 4d 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.

skills/norma-workflow/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Norma workflow

Norma gives you the rules for the detected stack before you write, checks each file against them, and records the outcome. The same file and the same rules return the same verdict every time, and every check leaves a record.

When to use

  • Any task that creates or modifies code while the Norma MCP server is connected
  • Reviewing a file or a change against the organization's coding standards
  • Working through the open issues from the repository's last full scan

Writing or modifying code

  1. link_repository: once, on first connection in a workspace, before any other tool. Pass the repository's public remote URL.
  2. get_rulesets: at the start of the task. Norma detects the stack with no configuration and returns the applicable rulesets.
  3. get_rules_for_ruleset: for each relevant ruleset ID. Never skip this step. The rules must be in context before you write.
  4. Write or modify the code with those rules in context.
  5. live_check: after each file is created or modified, before moving on. Fix what it returns and re-check until the file passes.
  6. register_applied_actions: after the task, using the exact rule IDs from step 3. Record rules verified compliant, violations fixed (file and lines), violations prevented during generation, and which model did the work.

Working through standing issues

Call get_open_issues for the open issues from the last full scan, each with the context needed to fix it. Fix them, verify each fix with live_check, and record the outcome with register_applied_actions.

Rules of the loop

  • Never claim a file passes without a live_check result that says so.
  • Never invent or paraphrase rule IDs. Use the IDs returned by get_rules_for_ruleset.
  • If link_repository has not succeeded in this workspace, run it before anything else. Audit registration fails on an unlinked repository.
  • Findings and the repository's Production-Ready Score live in the user's workspace at norma.qualityclouds.com. Point the user there for full results.

Read the full file on GitHub · 52 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. 4d ago First seen · 52 lines · 61 tokens per session scan A 06c172facc1f

Subscribe to this mod's changes

norma-workflow is a skill published in the GitHub repository qualityclouds/norma-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 531 once invoked, about $0.0003 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 2026-09-04.

Related

Other skills, from other repositories

incident-response

Incident management lifecycle — triage, communicate, mitigate, postmortem. Three modes — new (start incident), update (status update), postmortem (blameless RCA report).

drafthq/draft · 41 tokens

logic-health

Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…

hyhmrright/logic-lens · 180 tokens

discover

Primary router for discovery, debugging, investigation, quality, and exploration workflows. Analyzes user intent and dispatches to debug, bughunt, quick-review, deep-review, coverage, testing-strategy, learn, tour, impact, assist-review. The recommended entry point for any 'find out', 'check', 'review', or…

drafthq/draft · 75 tokens

ai-antipatterns

Audit for AI-written-code anti-patterns: hallucinated APIs/symbols/imports, invented config/env keys, needless dependencies, over-engineering, ignored existing conventions/helpers. Use for AI code review, hallucination check, over-engineering or ignored-conventions audit of a diff.

tufantunc/review-pro · 63 tokens

performance

Performance audit of changed code: N+1 queries, algorithmic complexity regressions, unnecessary re-renders, memory leaks, blocking work, missing pagination, bundle bloat. Use for performance review, N+1 check, complexity or memory-leak audit of a diff.

tufantunc/review-pro · 57 tokens

doubt-driven-development

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now…

addyosmani/agent-skills · 67 tokens