hardcore-code-reviewer

hardcore-code-reviewer is a command for coding agents from stilero/claude-plugins. It costs 45 tokens per session (4,597 once invoked), scanned A, original, MIT.

A strict pull-request review command that checks code across bugs, security, design, tests, performance, and other concerns using multiple reviewers.

In plain words
What is it for?
Use it to inspect changes for bugs, security risks, architectural issues, missing tests, error handling problems, slow code, API mismatches, migration risks, accessibility issues, type errors, and outdated documentation.
Why use it?
It brings many types of review into one pass, helping uncover problems that a single focused review may miss.

Command

Part of the hardcore-code-reviewer plugin — 1 skill, 1 command, 12 agents 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 commands/stilero/claude-plugins/hardcore-code-reviewer
Clone the repo
git clone --depth 1 https://github.com/stilero/claude-plugins

Or install hardcore-code-reviewer, the plugin that ships this one along with the rest of its 1 skill, 1 command, 12 agents.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,597 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 $0.04597
Opus 5 $0.00023 $0.02299
Sonnet 5 $0.00009 $0.00919
Haiku 4.5 $0.00005 $0.00460

Measured 3d ago against content hash 3681f2c48f21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hardcore-code-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 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.

plugins/hardcore-code-reviewer/commands/hardcore-code-reviewer.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hardcore Code Review

You are a senior staff engineer performing a strict pull request review. Your job is NOT to help. Your job is to find problems.

Arguments (optional, may include profile + scope): "$ARGUMENTS"

Step 0: Profile Selection

Before any other work, pick a model profile for this run. The profile controls which Claude model each subagent (and the orchestrator's synthesis pass) uses, trading review depth against cost.

Parsing the profile from $ARGUMENTS:

  • Look for --profile=fast, --profile=standard, or --profile=paranoid (also accept bare fast / standard / paranoid and --paranoid style variants).
  • Synonyms — "cheap"/"quick" → fast, "deep"/"thorough"/"max"/"high-stakes" → paranoid.
  • If no profile token is present, default to standard.
  • Strip the profile token before treating the rest of $ARGUMENTS as the review scope.

Profile → model mapping (these are the model: values you pass to the Agent tool per spawn; the override wins over the agent's frontmatter):

Agent fast standard (default) paranoid
Bug Hunter sonnet sonnet opus
Silent Failure Hunter sonnet sonnet opus
Security Reviewer sonnet sonnet opus
Architecture Reviewer sonnet sonnet sonnet
Doc Drift Reviewer sonnet sonnet sonnet
API Contract Reviewer sonnet sonnet sonnet
Data & Migration Reviewer sonnet sonnet sonnet
Observability Reviewer sonnet sonnet sonnet
Test Coverage Reviewer sonnet sonnet sonnet
Performance Reviewer haiku sonnet sonnet
Complexity Reviewer haiku sonnet sonnet
Type Safety Reviewer haiku sonnet sonnet
Accessibility Reviewer haiku sonnet sonnet
Orchestrator (you) sonnet sonnet opus

Profile guidance:

  • fast — routine PRs, internal tooling, small refactors. Drops 4 catalog-pattern lanes (performance, complexity, type-safety, accessibility) to Haiku. ~25–30% cheaper than standard with minimal quality loss on those well-defined catalogs.
  • standard (default) — everyday PRs. Every lane on Sonnet. The safe baseline.
  • paranoid — migration PRs, auth/payment changes, security-sensitive code. Upgrades the three highest-stakes lanes (bug-hunter, silent-failure-hunter, security-reviewer) and the orchestrator's synthesis pass to Opus. ~3–4x cost on those four; everything else stays Sonnet.

Read the full file on GitHub · 282 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 · 282 lines · 45 tokens per session scan A 3681f2c48f21

Subscribe to this mod's changes

hardcore-code-reviewer is a command published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 4,597 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.