Borrowing it
Nothing to install: this file belongs to 1cFE/fusion-tea. 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/1cFE/fusion-tea/main/.agents/skills/run-study/SKILL.mdgit clone --depth 1 https://github.com/1cFE/fusion-teaWrote 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/1cfe/fusion-tea/run-study)<a href="https://agentmods.dev/skills/1cfe/fusion-tea/run-study"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/run-study/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/1cfe/fusion-tea/run-study"><img src="https://agentmods.dev/badge/skills/1cfe/fusion-tea/run-study.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00172 | $0.01060 |
| Opus 5.5 | $0.00069 | $0.00424 |
| Sonnet 5.5 | $0.00034 | $0.00212 |
| Haiku 4.5 | $0.00017 | $0.00106 |
Grade A, and why
run-study 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 23d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Study
A study runs a model package over a set of parameter points and records what the model's own objective and constraints did at each one. What makes it a study rather than a sweep is the record: one directory that a second agent, with no memory of the run, can read and recover what was asked, what was assumed, what came out, and what none of it supports.
This file is the entry point and nothing else. It captures intake, picks the mode, names the record path, and points onward. The steps live in runbook.md; the rules live in the policy.
Three roles
- User — sets the intent, and rules on any axis the model turns out not to resist. That ruling happens before any point runs.
- Executor — works through the applicable runbook obligations and commits the record. May write an executor synthesis grounded only in the committed record; label its authorship honestly.
- Administrator — optional separate reader of a committed record, used when the owner requests a cold-record reading or independent coverage needs it. Reads only the record directory and reports missing facts instead of recovering them elsewhere.
The main agent may execute and synthesize directly. A separate administrator is not an automatic step. A claimed independent reading requires a fresh non-author session with no inherited conversation. Both kinds of synthesis cite only the committed record and preserve its evidence. Review scope follows the installed goal runbook, § Review scope and evidence reuse: original evidence, bounded briefs, and no duplicate assurance. A project without the goal layer applies the study policy's § Process sizing instead.
Pick the mode
- execute — there is an intent and no record yet. Ends with a committed record.
- administer — there is a committed record and no synthesis. Ends with
synthesis.md.
Infer the mode from the request and existing record. Ask only when genuine ambiguity would change the work. Executing and then synthesizing in the same session is allowed; a separate session is needed only for an independent reading.
What ships with it
4 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.
- 23d ago Changed · -14 lines · -3 tokens per session 1707a04eaae8
- 1mo ago Changed · -5 lines e3fe6bf94f78
- 2mo ago First seen · 78 lines · 175 tokens per session scan A 9c258fac57a1
run-study is a skill published in the GitHub repository 1cFE/fusion-tea (5 stars, last pushed 24d ago), licensed MIT. It adds 172 tokens to every session and 1,060 once invoked, about $0.0007 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 2026-08-31.
run-study compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| run-study1cFE/fusion-tea | Skill | 5 | 24d ago | MIT | A | 172 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |