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-refs-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-refs-reviewer)<a href="https://agentmods.dev/skills/wanghao9610/star/star-refs-reviewer"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-refs-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-refs-reviewer"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-refs-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Memory Poisoning · line 107 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00065 | $0.06231 |
| Opus 5 | $0.00032 | $0.03116 |
| Sonnet 5 | $0.00013 | $0.01246 |
| Haiku 4.5 | $0.00006 | $0.00623 |
Grade A, and why
star-refs-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 5d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Refs Reviewer
Invocation: star-refs-reviewer [PLAN_NAME | TOPIC | verify | organize | synthesize | survey [PLAN_NAME | TOPIC] | score | add PAPER… | ARXIV_ID | DOI | URL]. Resolve these modes before shared loading. No mode runs or resumes the full pass; a plan or topic scopes it. add and identifiers append papers. Load only the selected mode's references.
Shared conventions. Resolve the invocation target and mode first. Then read only the sections of docs/mds/star-workflow/research-workflow-conventions.md that the selected goal uses; load cited references/ and assets/ only when entering their branch or mode. Read .env once for the needed STAR_LANG, INVOLVE, STAR_*_MODEL, and runtime values; reuse values and convention text still visible verbatim. Resolve language under conventions §7.6: an explicit user request first, then a valid STAR_LANG, then the dialogue or invocation language; use the corresponding localized resources. SKILL_zh.md is for human readers and is never loaded at runtime. Preserve an existing document's frontmatter language. Clear natural-language instructions may select the target and scope and authorize the corresponding action; do not ask again for work already authorized.
Passing a tier model. Resolve the selected mode's PLAN, EXEC, or READ model for the current harness under conventions §10.8. Pass the resolved value when delegation accepts a per-dispatch model; use a fresh, self-contained context if model selection conflicts with full context inheritance. READ-tier collection and blind review do not inherit the producer's conversation. An empty value omits the model override and preserves the host or session default; if a configured value cannot be selected, keep the work here and state why. Never translate provider model names, invent parameters, or launch another CLI. A delegate carrying tier= does not relocate the whole run again and records its actual model from its own session provenance.
What ships with it
20 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.
- agents/openai.yaml 63 B
- assets/ref_analysis_template_zh.md 4.2 KB
- assets/ref_analysis_template.md 4.3 KB
- assets/refs_index_template_zh.md 3.3 KB
- assets/refs_index_template.md 3.4 KB
- assets/survey_template_zh.md 3.2 KB
- assets/survey_template.md 3.3 KB
- references/refs_rubric_zh.md 12 KB
- references/refs_rubric.md 12 KB
- references/score_spec_zh.md 1.2 KB
- references/score_spec.md 1.2 KB
- references/source_policy_zh.md 14 KB
- references/source_policy.md 14 KB
- references/survey_spec_zh.md 4.7 KB
- references/survey_spec.md 4.9 KB
- references/synthesize_spec_zh.md 2.3 KB
- references/synthesize_spec.md 2.4 KB
- references/venue_tiers_zh.md 3.5 KB
- references/venue_tiers.md 3.5 KB
- SKILL_zh.md 25 KB
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.
- 5d ago Changed · -31 lines · -161 tokens per session e5f132b000de
- 12d ago First seen · 148 lines · 226 tokens per session scan A 7520ef484239
star-refs-reviewer is a skill published in the GitHub repository wanghao9610/STAR (52 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 6,231 once invoked, about $0.0003 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.
Other skills, from other repositories
linear
Read Linear issues, transition state, and post comments. The entry point for ticket-driven agent workflows.
create-workflow
Use this skill to design, create, generate, convert, polish, or repair LazyMind Workflow artifacts.
interview-simulator
Simulate role-specific mock interviews, score each answer, and provide concrete feedback and model responses for interview preparation.
deep-research
A method for carrying out comprehensive research across multiple sources. It is intended for detailed investigations, comparisons, reviews, and landscape studies rather than simple factual lookups.
single-document-review
Use this skill when the user requests to review, analyze, critique, or summarize a SINGLE academic paper, general document, internal report, proposal, or web article. Supports comprehensive structured reviews covering methodology/logic assessment, strengths, weaknesses, and constructive feedback. Retrieves content…
sciverse-paper-search
Use this skill for scientific literature search, evidence retrieval, paper metadata screening, and cited research synthesis with Sciverse. This LazyLLM-adapted version supports SciverseSearch search, metasearch, metacatalog, and getcontent only; it does not assume full Sciverse MCP resource or attachment APIs are…