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-expt-analyst/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-expt-analyst)<a href="https://agentmods.dev/skills/wanghao9610/star/star-expt-analyst"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-expt-analyst/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-expt-analyst"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-expt-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 116 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 | $0.00064 | $0.04158 |
| Opus 5.5 | $0.00026 | $0.01663 |
| Sonnet 5.5 | $0.00013 | $0.00832 |
| Haiku 4.5 | $0.00006 | $0.00416 |
Grade A, and why
star-expt-analyst 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Experiment Analyst
Invocation: star-expt-analyst [PLAN_NAME | RUN_DIR | aggregate [PLAN_NAME] | watch [PLAN_NAME | RUN_DIR]] [DESCRIPTION]. Resolve aggregate and watch before loading the normal analysis workflow. A plan resolves through exec_runs; a run directory resolves back to its plan. With no settled target, list candidates and ask. watch is chat-only and authorizes no file write or successor action.
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).
Source bindings. Before reusing or finishing an analysis/results artifact, follow .agents/skills/star-flow-status/references/source_state.md (Chinese: source_state_zh.md). Record analysis against the leaf, relevant ancestors, EXEC_PLAN and actual raw evidence/configuration; record results against every included current analysis using --report. Check current input coverage with --require, including new runs/reports. A legacy or stale binding needs producer verification, not a date-based pass. A current engineering exemption in EXEC_LOG suppresses automatic missing-analysis work, never an explicit request to analyze; aggregate lists such runs separately without metrics. Watch remains chat-only. The helper writes only this skill's own report/table, after final content and provenance.
Role
Serve as the family's results auditor. star-plan-executor produces the run — code, artifacts, and a binary done-criterion verdict; star-code-reviewer audits the code that produced it; star-plan-reviser audits the plan text against execution evidence. This skill audits the results themselves: what did this run produce, did it finish, are the numbers healthy, do they meet what the plan expected, and what do they mean for the claim the plan traces to. The product is a persisted, evidence-backed analysis report. star-expt-digest reads across many of these to say what moved this period; it never re-scores a run, so a number belongs to whichever analysis first verified it.
What ships with it
13 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 62 B
- assets/expt_analysis_template_zh.md 5.4 KB
- assets/expt_analysis_template.md 5.3 KB
- assets/results_template_zh.md 4.0 KB
- assets/results_template.md 4.1 KB
- references/aggregate_spec_zh.md 9.8 KB
- references/aggregate_spec.md 10 KB
- references/aggregate_step_zh.md 2.0 KB
- references/aggregate_step.md 2.1 KB
- references/analysis_rubric_zh.md 13 KB
- references/analysis_rubric.md 13 KB
- references/watch_step_zh.md 1.2 KB
- references/watch_step.md 1.2 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.
- 14d ago Changed · +2 lines 9f98cd0906cb
- 1mo ago Changed · +7 tokens per session ea6cd9b061a6
- 2mo ago Changed · -23 lines · -148 tokens per session ba8517616c61
- 2mo ago First seen · 140 lines · 205 tokens per session scan A a9fdb2e6c1af
star-expt-analyst is a skill published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 4,158 once invoked, about $0.0003 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-expt-analyst compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-expt-analystwanghao9610/STAR | Skill | 54 | 2d ago | MIT | A | 64 | 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 |