Borrowing it
Nothing to install: this file belongs to wanghao9610/STAR. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wanghao9610/STAR/main/.agents/skills/star-code-reviewer/SKILL.mdgit clone --depth 1 https://github.com/wanghao9610/STARWrote 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/skills/wanghao9610/star/star-code-reviewer)<a href="https://agentmods.dev/skills/wanghao9610/star/star-code-reviewer"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-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/skills/wanghao9610/star/star-code-reviewer"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 29 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 82 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.05146 |
| Opus 5.5 | $0.00023 | $0.02058 |
| Sonnet 5.5 | $0.00012 | $0.01029 |
| Haiku 4.5 | $0.00006 | $0.00515 |
Grade A, and why
star-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 14d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Code Reviewer
Invocation: star-code-reviewer [PLAN_NAME | PATH | diff | GIT_RANGE] [DESCRIPTION]. A plan selects its implementation and conformance evidence; a path, diff, or git range selects those files. An explicit user invocation with no scope target reviews all of ${CODE_NAME}/; a description asking for review only limits what the run may write, not what it reads. A natural-language or automatic pickup uses the narrowest scope established by that request or current work and asks if none is settled. Expand only to files required to verify cross-file imports, APIs, schemas, or contracts, and record why each was added. A review-only/read-only request writes the report and stops: it applies no fixes, makes no fix commit, and starts no writing successor. A specific request to fix findings authorizes eligible fixes within its stated scope; reuse it without another question.
Shared conventions. Follow docs/mds/star-workflow/research-workflow-conventions.md for scope, authority, .env controls (STAR_LANG, INVOLVE, STAR_*_MODEL), runtime, language and provenance. Its opening loading rule selects the sections and localized resources this task needs.
Passing a tier model. Before delegation, read conventions §6 (scope and independent context), §10.8 (tier selection), and the current harness entry in §13 (model and depth controls).
Authorization context. Trace fix authority to the user's explicit fix request or to the parent run's recorded star-auto request, goal and limits (conventions §10.7). auto=unattended carries that context; a token alone establishes no fix authority. Preserve a review-only request and host-required approvals. Apply the research-scope and source-material boundaries in the conventions opening, and distinguish technical failures from policy interventions under §10.8 before retrying or changing a model.
Role
Serve as the family's code auditor. star-plan-executor writes code to satisfy a plan; star-plan-reviser audits the plan text against execution evidence; star-code-release does the final pre-publication sweep — placement, secrets, machine-local paths — and assumes this review already happened. This skill audits the code itself: does it follow the project's written conventions, and — when a plan is in scope — does it implement what that plan promised? The product is a persisted, evidence-backed review report, plus only the mechanical fixes already authorized by the request or the limited auto=unattended grant.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 14d ago Changed · +8 lines 8cf6ada6bdfd
- 1mo ago Changed · +2 lines 5470f713eacf
- 1mo ago Changed · +1 lines d4ecf833589e
- 2mo ago Changed · -28 lines · -140 tokens per session 03645cf6cf89
- 2mo ago First seen · 131 lines · 198 tokens per session scan A e6bf361c278b
star-code-reviewer is a skill published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 5,146 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 2026-08-30.
star-code-reviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-code-reviewerwanghao9610/STAR | Skill | 54 | 2d ago | MIT | A | 58 | Codex |
| plot_skillsLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| open-code-reviewalibaba/open-code-review | Skill | 50k | yesterday | Apache-2.0 | A | 98 | Cursor |
| verify-changefengshao1227/ccg-workflow | Skill | 6.0k | 4d ago | MIT | A | 65 | Claude Code |
| verify-modulefengshao1227/ccg-workflow | Skill | 6.0k | 4d ago | MIT | A | 61 | Claude Code |
| verify-qualityfengshao1227/ccg-workflow | Skill | 6.0k | 4d ago | MIT | A | 64 | Claude Code |
| company-researchPrism-Shadow/penguin-harness | Skill | 3.2k | yesterday | Apache-2.0 | A | 80 | Claude Code, Codex |