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 release-codegit 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/release-code)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/release-code"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/release-code/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/release-code"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/release-code.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 | $0.00078 | $0.01017 |
| Opus 5.5 | $0.00031 | $0.00407 |
| Sonnet 5.5 | $0.00016 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
release-code 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Code
A public release lets others reproduce the paper's results and understand the method without seeing internal paths, secrets, abandoned experiments, or development history. The development repository stays the single source of truth: the release is regenerated from it, never developed in parallel.
Define what the release must support
Start from the claims the release backs: the results reported in the paper, or a subset of Runs the user selects. The release reproduces those claims, not every Run Record in the project. For each claim, record the reported value, the tolerance within which a reproduction counts, and the Run that produced it when one exists; the Run supplies the exact conditions, such as config, checkpoint, and data. Keep this scope in a release Spec of type capability through manage-specs: one AC-NN per claim with its reported value, tolerance, and Run IDs, the code paths included, explicit exclusions, the license, third-party code and its licenses, and the public repository. A claim whose producing conditions cannot be found is reported as such, not released on trust.
Trace the minimal code path
From each Run's entry and effective config, follow imports and config references to the code actually executed, and bring only that path. Fast research iteration often leaves several copies of one script that differ by constants; release one parameterized entry point with the variants as configs. Rewrite for readability where needed without changing the computation. Leave out dead experiments, cluster launch wrappers, and debugging switches.
Assemble on an isolated branch
The public repository must never receive development history. By default, create an orphan branch named release, check it out in a separate worktree outside the development tree, such as ../<repo>-release, add the public repository as remote public, and map pushes to that branch only:
git config remote.public.push refs/heads/release:refs/heads/main
What ships with it
6 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 045fcd1209dc
- 8d ago First seen · 45 lines · 78 tokens per session scan A 7ad27a8c6847
release-code is a skill published in the GitHub repository Tx1207/hello-scholar (10 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 1,017 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 2026-10-22.
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.