Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Tx1207/hello-scholar --skill record-experimentgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/record-experiment)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/record-experiment"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/record-experiment/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/tx1207/hello-scholar/record-experiment"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/record-experiment.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 | $0.00056 | $0.00992 |
| Opus 5.5 | $0.00022 | $0.00397 |
| Sonnet 5.5 | $0.00011 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
record-experiment 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 4d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record Experiment
Make one execution understandable, recoverable, and reusable: what question it addressed, what it reused, what actually ran, and what the evidence supports. The main agent and the owning Spec keep the research design and cross-Run decisions.
Start from prior Runs
Before planning a new execution, scan runs/INDEX.md by entry point and topic, then search Records, configs, runs/*/results/, and artifacts/ for the same or an overlapping question. Prefer reusing a result, running only the missing cells, or rerunning an existing entry point with changed arguments over writing a new script. When a new Run builds on an earlier one, set derived_from to that Run and state what differs and which artifacts are reused, so a reader sees the change without comparing two Records.
Decide what is worth preserving
Judge by how the evidence will be used, not by the command name, runtime, hardware, or output files. Preserve a comparison, ablation, or calculation that informs a research conclusion or later choice, even when tiny or negative, and preparation or failure evidence that materially supports reproduction, recovery, or a resource decision. Imports, connectivity and configuration checks, startup smoke, static checks, and polling create no separate Run; keep them in task verification or in the planned Record of the experiment they prepare. Summaries and reports create no Run. A read-only query stays read-only even when it discovers a new fact. Read references/examples.md for boundary cases.
Create one identity
Use runs/<run-id>/record.md, where <run-id> is YYYYMMDD-HHMM-<short-topic> with a seed suffix when useful. Never overwrite or repurpose an existing directory; add a numeric suffix for a distinct Run. Read references/status-and-fields.md before creating or closing a Record; hello-scholar docs check enforces its fields and lifecycle.
One Run is one research execution. Startup errors, fixes, and retries before it starts are appended to its planned Record. After a research execution fails or ends, another execution is a new Run that sets derived_from to the earlier one, reuses its launch plan, and resumes from completed stages or checkpoints when conditions allow. For an already executed experiment, record the available evidence and its gaps afterward without rerunning.
What ships with it
8 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.
- 4d ago Changed 18df5f898a4c
- 8d ago Changed 3b5b5c541be3
- 9d ago Changed · +21 tokens per session 172bb46e139b
- 1mo ago Changed · -72 lines · -38 tokens per session 4a54f597ebe9
- 2mo ago First seen · 107 lines · 73 tokens per session scan A 97e72d27d461
record-experiment is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 992 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 2026-08-31.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.