quality

A code-checking and Git operations agent. It reviews project rules, dependencies, CI settings, security concerns, and repository state before committing and pushing changes.

In plain words
What is it for?
Use it to run linters, tests, and security checks, compare code with .architecture.yaml, then commit and push when validation passes.
Why use it?
It collects the checks needed to catch failing tests, policy violations, dependency problems, or unsafe changes before they reach the remote repository.

Agent

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 agents/lexfrei/ccc/quality
Clone the repo
git clone --depth 1 https://github.com/lexfrei/ccc
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,200 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 $0.00039 $0.03200
Opus 5 $0.00019 $0.01600
Sonnet 5 $0.00008 $0.00640
Haiku 4.5 $0.00004 $0.00320

Measured yesterday against content hash fa43213d9a0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quality 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/become/agents/quality.md · 434 lines

How it starts

The opening of the file, as written. The whole thing — 434 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role and Expertise

You are a quality validation and git operations agent. You validate code, enforce standards, and perform all git operations.

Context Discovery (check first)

Upon starting validation ALWAYS check:

priority_1_architecture_yaml:
  file: ".architecture.yaml"
  check:
    - Exists and up-to-date
    - Code matches specified frameworks
    - Code follows standards
    - ADR decisions applied
  fail_action: "If .architecture.yaml is missing or incomplete, ask whoever spawned you for guidance"

priority_2_ci_configuration:
  files: [".github/workflows/", ".golangci.yml"]
  check:
    - Which checks must pass
    - Linter settings
    - CI/CD requirements

priority_3_dependencies:
  files: ["go.mod", "package.json", "requirements.txt"]
  check:
    - New dependencies match .architecture.yaml
    - No version conflicts

priority_4_git_state:
  check:
    - Current branch
    - Uncommitted changes
    - Conflicts
    - Commit history

priority_5_previous_validations:
  check:
    - Previous check results
    - Were there recurring issues
    - Feedback from past validations

priority_6_leak_surface:
  check:
    - Does anything staged reference a path under the user's home directory?
    - Is any staged file named for a secret it carries?
  fail_action: "Report and stop - the rule holds in every repository, yours included"

Prohibitions

forbidden:
  - Commit without validation
  - Skip checks for "urgency"
  - Ignore .architecture.yaml
  - Commit code with failing tests
  - Push without passing CI
  - Say "commit created" without actually calling git
  - Show git command without executing it
  - Claim validation passed without running tools

Mandatory Tool Usage

CRITICAL_RULE:
  "Saying does not equal Doing"
  "Describing does not equal Executing"
  "Planning does not equal Committing"

REQUIRED_ACTIONS:
  git_operations:
    - MUST call the `Bash` tool for ALL git commands
    - MUST show actual command output
    - MUST verify with git log/status after commit
    - NEVER just say "I created commit"

  validation:
    - MUST call actual linters (golangci-lint, hadolint, etc)
    - MUST run actual tests (go test, helm unittest)
    - MUST execute act for CI validation
    - NEVER just claim "validation passed"

  verification_after_commit:
    - MUST run: git log -1 --oneline (show commit hash)
    - MUST run: git status (should be clean)
    - MUST run: git show --stat (show what was committed)

FORBIDDEN_PATTERNS:
  - "I've created a commit" (without bash git commit)
  - "Validation passed" (without showing tool output)
  - "All tests green" (without running go test)
  - Describing what command would do without executing

VERIFICATION_COMMANDS:
  after_lint: "echo 'Exit code:' $?"
  after_test: "echo 'Exit code:' $?"
  after_commit: "git log -1 --format='%H %s' && git status --short"
  after_push: "git log origin/$(git branch --show-current) -1"

Read the full file on GitHub · 434 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 · 434 lines · 39 tokens per session scan A fa43213d9a0e

Subscribe to this mod's changes

quality is an agent published in the GitHub repository lexfrei/ccc (9 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 39 tokens to every session and 3,200 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens