warden

A code-review checklist that compares your changes with example files and the project's written conventions before you open a pull request.

In plain words
What is it for?
Use it after finishing code to check every changed file against documented rules and approved examples.
Why use it?
It helps catch style and project-rule disagreements early, reducing review rework.

Skill for Claude CodeCodex

Part of the fellowship plugin — 20 skills, 19 commands, 6 agents, 3 hooks shipped together

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/justinjdev/fellowship/warden
Any agent
npx skills add justinjdev/fellowship --skill warden
Clone the repo
git clone --depth 1 https://github.com/justinjdev/fellowship

Made for: Claude Code, Codex.

Or install fellowship, the plugin that ships this one along with the rest of its 20 skills, 19 commands, 6 agents, 3 hooks.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,007 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 $0.00045 $0.01007
Opus 5 $0.00023 $0.00504
Sonnet 5 $0.00009 $0.00201
Haiku 4.5 $0.00005 $0.00101

Measured 3d ago against content hash f1ab30075a65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

warden 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 3d 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.

plugin/skills/warden/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Warden — Catch Convention Violations Before Your Reviewer Does

Overview

Strict review simulation. Compares your code against the project's reference files and documented conventions, flagging every deviation. The goal is to catch the feedback that causes multi-day review rework before you open the PR.

When to Use

  • Code is functionally complete and you're about to open a PR
  • Any time you've written more than ~50 lines of new code
  • Working in an area where past reviews have been painful

Process

Step 1: Gather Context

Read three things:

  1. Your changes — every file modified or created in this PR
  2. Reference files — from CLAUDE.md ## Reference Files section for the relevant area
  3. Conventions — from CLAUDE.md ## Review Conventions section

If reference files aren't documented, ask:

"I need reference files to compare against. Can you point me to a similar file that your reviewer would approve of?"

If conventions aren't documented, proceed with reference file comparison only and note: "You should run /chronicle to build up your conventions list."

Step 2: Convention Check

For every rule in ## Review Conventions, check compliance:

| # | Convention | Status | Detail |
|---|-----------|--------|--------|
| 1 | [rule text] | PASS/FAIL/N/A | [specific evidence] |
| 2 | ... | ... | ... |

Step 3: Reference Comparison

Compare your code against reference files across every dimension:

Structure

  • File organization matches reference
  • Import ordering matches reference
  • Section ordering matches reference

Patterns

  • Dependency access matches reference approach
  • Error handling follows same pattern (types, propagation, messaging)
  • Data flow follows same layers
  • No bypassed abstractions (e.g., direct DB calls when reference uses repository)

Naming

  • Variable naming matches reference style
  • Function naming matches reference verb patterns
  • Type/interface naming matches reference conventions

Read the full file on GitHub · 121 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. 3d ago First seen · 121 lines · 45 tokens per session scan A f1ab30075a65

Subscribe to this mod's changes

warden is a skill published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 20d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,007 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.