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 sutchan/Agent-Skills-Hub --skill ai-research-reproductiongit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/ai-research-reproduction)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/ai-research-reproduction"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/ai-research-reproduction/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/sutchan/agent-skills-hub/ai-research-reproduction"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/ai-research-reproduction.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 | $0.00058 | $0.01518 |
| Opus 5.5 | $0.00023 | $0.00607 |
| Sonnet 5.5 | $0.00012 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
ai-research-reproduction 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 19d 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.
This is a copy
97% identical to ai-research-reproduction — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-research-reproduction
Purpose
Guide README-first deep learning reproduction toward the smallest trustworthy run with auditable evidence. Preserve documented meaning; record assumptions, deviations and blockers instead of changing semantics to manufacture success. Load specialized references only for a concrete uncertainty.
Fast Path
For a routine bounded run, keep the control path short:
- Read the target README and only the target test/config/source needed to understand the documented command.
- Run
scripts/orchestrate_repro.py --repo <repo> --plan-only --agent-outputwith any explicit user timeout bound (--timeoutor--train-timeout) already supplied; reviewcommand_candidates, the selectedcmd-XX, side-effect contract, selection fingerprint, and returnedreviewed_run_args. With no--output-dir, later evidence goes to<repo>/repro_outputsregardless of caller cwd. - Run the selected candidate, or another reviewed candidate, with
--run-selected --command-id <cmd-XX> --plan-fingerprint <fingerprint> --agent-outputplus requested timeout/metric/source-adjacent options. Preserve an explicit user command-timeout bound instead of silently making it stricter on a routine trusted run.--timeoutlimits the target command; do not wrap the whole orchestrator in an equal or shorter external timeout, because it still needs time to terminate children and write terminal evidence. A changed command set fails closed; setup/download commands are never target candidates. - Run
--verify-output --agent-output; inspect detailed evidence files only when verification fails or the result is partial/blocked. - Deliver the bounded result and stop.
For a host with short tool-call deadlines, rerun planning with --include-agent-handoff and follow references/agent-job.md; otherwise keep the direct path above. Job completion is not task acceptance, and uncertain state is never a reason for automatic replay.
Do not inspect orchestrate_repro.py, annotate_readme.py, _bundled/, writers, or runtime internals on a normal success path. Inspect implementation only for a concrete blocker, unexpected side effect, bundle-integrity failure, or unresolved safety question. Use scripts/doctor.py for first-use environment/install diagnostics. Executed commands keep full lifecycle/log evidence under repro_outputs/_runtime/<run_id>/.
What ships with it
39 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.
- _bundled/MANIFEST.json 5.3 KB
- _bundled/shared/scripts/agent_provider.py 6.1 KB runs code
- _bundled/shared/scripts/command_utils.py 3.0 KB runs code
- _bundled/shared/scripts/lessons_store.py 8.4 KB runs code
- _bundled/shared/scripts/model_adapter.py 6.3 KB runs code
- _bundled/shared/scripts/resource_monitor.py 8.0 KB runs code
- _bundled/shared/scripts/runtime_runner.py 28 KB runs code
- _bundled/shared/scripts/task_queue.py 30 KB runs code
- _bundled/shared/scripts/write_explore_bundle.py 33 KB runs code
- _bundled/shared/scripts/write_run_bundle.py 31 KB runs code
- agents/openai.yaml 389 B
- assets/COMMANDS.template.md 348 B
- assets/LOG.template.md 669 B
- assets/model_profile.template.json 183 B
- assets/PATCHES.template.md 525 B
- assets/readme_annotations.template.json 1.1 KB
- assets/status.template.json 1.1 KB
- assets/SUMMARY.template.md 621 B
- references/agent-job.md 5.5 KB
- references/agent-operating-principles.md 2.7 KB
- references/agent-runner.md 10 KB
- references/architecture.md 1.3 KB
- references/continuous-learning-policy.md 3.7 KB
- references/deep-learning-experiment-principles.md 2.0 KB
- references/explore-variant-spec.md 4.1 KB
- references/language-policy.md 794 B
- references/output-spec.md 9.0 KB
- references/patch-policy.md 1.6 KB
- references/readme-annotation-policy.md 4.3 KB
- references/research-pitfall-checklist.md 1.6 KB
- references/research-rigor-principles.md 3.7 KB
- references/research-safety-principles.md 1.9 KB
- references/research-thinking-loop.md 4.1 KB
- references/runtime-and-model-adapter.md 5.3 KB
- scripts/annotate_readme.py 36 KB runs code
- scripts/doctor.py 3.5 KB runs code
- scripts/orchestrate_repro.py 115 KB runs code
- scripts/repro_job.py 19 KB runs code
- scripts/run_agent.py 38 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.
- 19d ago Changed · +1 lines 1f64b28dd791
- 25d ago Changed · -20 lines · -78 tokens per session 19689aa892b8
- 1mo ago Changed · -4 lines · +78 tokens per session 7cc128f04cc0
- 1mo ago First seen · 135 lines · 58 tokens per session scan A 52d9ec63c1b1
ai-research-reproduction is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 1,518 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 97% identical to ai-research-reproduction, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
using-opentikz
Use when a user wants a TikZ figure for a paper — an icon, an editable architecture/pipeline/flow template, or an example — and wants you to find, edit, and verify it. The single repo-wide skill for working with the OpenTikZ library.
rowan
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve…
paper-2-web
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, or Paper2Poster conference posters from LaTeX or PDF sources.
performing-causal-analysis
Estimate causal effects from existing data. Use when fitting or interpreting DiD, ITS, synthetic control, regression discontinuity, or other treatment-effect analyses, including robustness checks and counterfactual plots. For choosing a study design before analysis, use designing-experiments instead.
skill-index-updater
Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for refreshing indexed repos (refresh-index), improving skills (skill-creator), or install.
literature-searcher
Search CrossRef, OpenAlex, PubMed, Semantic Scholar, and optional Scopus; deduplicate results, download open-access PDFs by DOI, classify papers, monitor new results, and analyze coverage. Use when asked to search literature, monitor a topic, download an open-access paper, classify papers, or analyze literature gaps.