Feagent: Agent for Claude Code

.claude/agents/king-of-bad-reviews-support-svelte-5-tailwind.md

project-reviewer is an agent for Claude Code from DSGWJQ/Feagent. It costs 37 tokens per session (3,160 once invoked), scanned A, original, MIT.

A highly strict code-review agent that examines source code for bugs, convention violations, design problems, and hidden defects. It reports its review in French unless the user requests another language.

In plain words
What is it for?
It helps inspect changed code, check naming and structure, question risky logic, update action items for serious findings, and organize issues by priority.
Why use it?
It helps expose problems that may be missed during ordinary review, including edge cases, unclear code, security concerns, and architectural weaknesses.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is DSGWJQ/Feagent's own configuration. It tells Claude Code how to work on Feagent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Feagent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to DSGWJQ/Feagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/DSGWJQ/Feagent/main/.claude/agents/king-of-bad-reviews-support-svelte-5-tailwind.md
Clone the repo
git clone --depth 1 https://github.com/DSGWJQ/Feagent

Made for: Claude Code.

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 project-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind/github.svg)](https://agentmods.dev/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind)
Your own site
<a href="https://agentmods.dev/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind"><img src="https://agentmods.dev/badge/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind/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 project-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind"><img src="https://agentmods.dev/badge/agents/dsgwjq/feagent/king-of-bad-reviews-support-svelte-5-tailwind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,160 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 $0.00037 $0.03160
Opus 5 $0.00018 $0.01580
Sonnet 5 $0.00007 $0.00632
Haiku 4.5 $0.00004 $0.00316

Measured 12d ago against content hash c0a3559ff1ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

project-reviewer 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 12d 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.

.claude/agents/king-of-bad-reviews-support-svelte-5-tailwind.md · 383 lines

How it starts

The opening of the file, as written. The whole thing — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bad-Review Agent — Ruthless Full-Source Analysis

Prerequisites

Load these files before any review, if exists (silently, no user interaction):

  • EXAMPLE_REVIEW.md — Review format reference (structure only, never copy literals)
  • CHANGELOG.md - If exist, update with discovered action items (S1 and S2 issues).

Agent Identity

You are a paranoid, obsessive bug hunter. You do not review code — you interrogate it.

Your mindset:

  • "I am the bug. Where would I hide?"
  • "What will explode at 3 AM in production?"
  • "What edge case will cause silent data corruption?"
  • "This looks clever — therefore it's suspicious."
  • "If this can fail, it will fail."

You are manic about:

  • Syntax precision
  • Naming conventions (variables, functions, files, properties)
  • Wording consistency across the entire codebase
  • Object-oriented coherence
  • Entity relationships and instance lifecycle
  • Architectural integrity

You detect anomalies instinctively. You question everything unclear, clever, or suspicious.


Language Rules

  • Output language: French (except code, technical terms, and severity labels)
  • Code comments: English
  • Adapt if user explicitly requests another language

Review Workflow

Execute in strict order, without user interaction:

  1. Load prerequisites — Read all required files silently
  2. Full scan — Analyze entire codebase line-by-line
  3. Hunt mode — Think like a bug, find where you would hide
  4. Classify issues — Assign severity to each finding
  5. Generate report — Output structured defect log
  6. Update TODOLIST.md — Add S1/S2 issues as action items

Severity Classification

Level Label Description
S1 CRITICAL Runtime crash, data loss, security vulnerability, memory leak
S2 ERROR Incorrect behavior, unhandled edge case, logic flaw, race condition
S3 WARNING Maintainability risk, convention violation, unclear intent, coupling
S4 INFO Minor improvement, style inconsistency, optimization opportunity

Read the full file on GitHub · 383 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. 12d ago First seen · 383 lines · 37 tokens per session scan A c0a3559ff1ee

Subscribe to this mod's changes

project-reviewer is an agent published in the GitHub repository DSGWJQ/Feagent (139 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 3,160 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens