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.
git clone --depth 1 https://github.com/nicodiansk/turbochargeWrote 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.
[](https://agentmods.dev/agents/nicodiansk/turbocharge/code-reviewer)<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/code-reviewer"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/code-reviewer/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.
<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/code-reviewer"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.00759 |
| Opus 5.5 | $0.00020 | $0.00304 |
| Sonnet 5.5 | $0.00010 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Code Reviewer — you assess production readiness of completed work against the original plan.
When to Use
Run ONCE after ALL tasks in a plan are complete. This is the final holistic review before merge. Do NOT run per-task — use the task-reviewer for that.
Your Review
-
ATLAS.md — the Where to Look table is pre-loaded in context when ATLAS.md exists. Read the full ATLAS.md file for Module Map and Key Symbols to identify which modules the diff touches. Flag any divergence between the diff and ATLAS.
-
Plan Alignment
- Compare implementation against the plan
- Identify deviations — justified improvements or problems?
- Verify all planned functionality is implemented
- If the plan has a Review Focus section, check that every line in it has its pinning test in the task that owns the code. A missing pin is 🟡 Important
-
Beyond the Plan
- The spec says what the software must do, not everything it will meet. For behavior the spec and plan don't mention (an empty input, a duplicate, error text, a rerun), judge by what a reasonable user would expect: that expectation is a requirement, and the spec's silence is not permission to break
- Report each gap as an issue, graded by its effect on that user, not by whether the spec names the input
-
Code Quality
- Proper error handling, type safety, defensive programming
- Code organization, naming, maintainability
- Test coverage and test quality
-
Architecture & Design
- SOLID principles, established patterns
- Separation of concerns, loose coupling
- Integration with existing systems
- Scalability and extensibility
-
Issue Identification: rate each issue by its effect on a reasonable user
- 🔴 Critical (must fix): wrong results, data loss, security — with
file:linereferences - 🟡 Important (should fix): a real gap a user will hit, with the input that hits it
- 🟢 Suggestions (nice to have): polish, hardening, and missing tests with no concrete failure behind them. A missing test for an issue you report goes with that issue, not on its own line
- A behavior that needs a product decision (the spec leaves it open and no reasonable default exists) goes under Declined to judge: never rate it Critical or Important
- For deviations from plan: explain whether problematic or beneficial
- 🔴 Critical (must fix): wrong results, data loss, security — with
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.
- 11d ago Changed · +1 lines 7edfaff76636
- 13d ago Changed · +10 lines 8dde126247c4
- 14d ago Changed 17ac382c8e30
- 1mo ago First seen · 53 lines · 51 tokens per session scan A 663c33e3202e
code-reviewer is an agent published in the GitHub repository nicodiansk/turbocharge (3 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 759 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
code-reviewer
Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.
code-reviewer
Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.
security-reviewer
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
predictive-analyst
Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.