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-metd-summarize/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-metd-summarize)<a href="https://agentmods.dev/skills/wanghao9610/star/star-metd-summarize"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-metd-summarize/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-metd-summarize"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-metd-summarize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.03849 |
| Opus 5.5 | $0.00023 | $0.01540 |
| Sonnet 5.5 | $0.00012 | $0.00770 |
| Haiku 4.5 | $0.00006 | $0.00385 |
Grade A, and why
star-metd-summarize 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Method Summarizer
Invocation: star-metd-summarize [overview | dataset | framework | training | evaluation] [DESCRIPTION]. Resolve the output first; no output compiles all five in dependency order, with overview last. Natural language may authorize a draft or overwrite when it clearly names that operation and scope; otherwise preserve the readiness and overwrite gates.
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.
Resolve the output mode before running scripts/scan.sh --slim; treat its plan frontmatter, sub-plan indexes, and placeholder counts as the readiness check's input, and its metds/ artifact frontmatter as the input to Step 5's stale check. The run-log and wkdrs/ lines the scan also prints are not read (Principle 1). If it fails, read the plan files directly and report the fallback.
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).
Source bindings. Follow .agents/skills/star-flow-status/references/source_state.md (Chinese: source_state_zh.md) for method-document freshness. Record method against every live plan consulted for content, readiness or source selection using --method-plan; bind configuration files that supplied facts too. On reuse, require the current scoped plan inventory so added sources cannot be missed. Record only after final authorized writes and source verification; dates remain provenance. The shell helper writes only the current method document and runs no experiment or interpreter.
Role
You are the family's method compiler. star-plan-coach and star-plan-decomposer author the plans; star-plan-executor keeps them true to what was executed; star-plan-reviser corrects them against evidence. This skill compiles them: the plan tree is organized by decomposition and execution order; it reorganizes the same facts along the axis a reader needs — what the method is, what data it eats, how it is trained, how it is judged. The product is the five documents under metds/, the material a paper's method section is written from. This skill runs once the loop has closed — every leaf executed, every top-level plan finalized, the method determined: while the method is still moving, the plans are the deliverable, not these documents.
What ships with it
14 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 64 B
- assets/dataset_template_zh.md 3.0 KB
- assets/dataset_template.md 3.1 KB
- assets/evaluation_template_zh.md 3.0 KB
- assets/evaluation_template.md 3.1 KB
- assets/framework_template_zh.md 2.6 KB
- assets/framework_template.md 2.7 KB
- assets/overview_template_zh.md 2.4 KB
- assets/overview_template.md 2.5 KB
- assets/training_template_zh.md 2.6 KB
- assets/training_template.md 2.6 KB
- references/extract_map_zh.md 9.9 KB
- references/extract_map.md 10 KB
- scripts/scan.sh 25 KB runs code
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 · +2 lines 95d7f3f9322e
- 1mo ago Changed b89f545dbe3d
- 2mo ago Changed · -25 lines · -150 tokens per session e32086080caa
- 2mo ago First seen · 126 lines · 208 tokens per session scan A b3d191fe577b
star-metd-summarize 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 3,849 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-metd-summarize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-metd-summarizewanghao9610/STAR | Skill | 54 | 2d ago | MIT | A | 58 | Codex |
| plot_skillsLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |
| autoresearchOrchestra-Research/AI-Research-SKILLs | Skill | 14k | 26d ago | MIT | A | 98 | Claude Code, Codex |
| company-researchPrism-Shadow/penguin-harness | Skill | 3.2k | yesterday | Apache-2.0 | A | 80 | Claude Code, Codex |
| figure-composerUnicomAI/wanwu | Skill | 2.4k | 14d ago | Apache-2.0 | A | 169 | Claude Code, Codex |
| paper-narrativeUnicomAI/wanwu | Skill | 2.4k | 14d ago | Apache-2.0 | A | 155 | Claude Code, Codex |
| create-workflowLazyAGI/LazyMind | Skill | 589 | yesterday | Apache-2.0 | A | 0 | Claude Code, Codex |