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-digest/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-digest)<a href="https://agentmods.dev/skills/wanghao9610/star/star-expt-digest"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-expt-digest/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-digest"><img src="https://agentmods.dev/badge/skills/wanghao9610/star/star-expt-digest.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 101 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 | $0.00065 | $0.03717 |
| Opus 5.5 | $0.00026 | $0.01487 |
| Sonnet 5.5 | $0.00013 | $0.00743 |
| Haiku 4.5 | $0.00006 | $0.00372 |
Grade A, and why
star-expt-digest 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Experiment Digest
Invocation: star-expt-digest [PLAN_NAME | <N>d | <YYYY-MM-DD> | all | ledger] [DESCRIPTION]. Resolve ledger before loading window rules. Otherwise a plan covers its family, a duration or date sets a window, all covers history, and no argument resumes after the newest covers.through among incremental, window and all digests. Natural language may set emphasis but does not silently change the resolved scope.
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).
Engineering and source status. Use .agents/skills/star-flow-status/references/source_state.md (Chinese: source_state_zh.md) when classifying a missing analysis or checking a results table. A current engineering exemption is listed as engineering work with no metrics, excluded from missing-analysis gaps and numeric comparisons; an invalid exemption routes to its executor. A results table is current only when its content binding covers the current eligible analysis reports. This does not turn the digest into a raw-result auditor or change its date-window semantics.
Role
Serve as the family's timekeeper. star-expt-analyst answers did this run meet its plan; its aggregate mode answers what are the final numbers, organised by claim and owns the verified results table wkdrs/results/results.md; star-flow-status answers where does everything stand right now — a snapshot with no memory. This skill answers what none of them can: what has happened since last time, and what did we learn.
The product is a dated digest — what a researcher reads back before a supervisor meeting, a weekly report, or picking work up after two weeks away. It carries narrative the results table is forbidden to carry: what moved, what got refuted, which direction changed. It is not a results table, and never the source anyone quotes a number from.
What ships with it
12 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 61 B
- assets/digest_template_zh.md 5.8 KB
- assets/digest_template.md 6.0 KB
- assets/model_ledger_template_zh.md 3.3 KB
- assets/model_ledger_template.md 3.4 KB
- references/digest_rubric_zh.md 7.4 KB
- references/digest_rubric.md 7.8 KB
- references/ledger_spec_zh.md 1.9 KB
- references/ledger_spec.md 1.9 KB
- references/scope_spec_zh.md 6.0 KB
- references/scope_spec.md 5.9 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 c58902bab37e
- 1mo ago Changed 4e45fd45315e
- 2mo ago Changed · -27 lines · -140 tokens per session cf19ead6b1df
- 2mo ago First seen · 131 lines · 205 tokens per session scan A 97557b2ba4cc
star-expt-digest is a skill published in the GitHub repository wanghao9610/STAR (54 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 3,717 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-digest compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| star-expt-digestwanghao9610/STAR | Skill | 54 | 2d ago | MIT | A | 65 | 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 |