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 flonat/flonat-research --skill computational-experimentsgit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/computational-experiments)<a href="https://agentmods.dev/skills/flonat/flonat-research/computational-experiments"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/computational-experiments/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/flonat/flonat-research/computational-experiments"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/computational-experiments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 156 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00043 | $0.03873 |
| Opus 5.5 | $0.00017 | $0.01549 |
| Sonnet 5.5 | $0.00009 | $0.00775 |
| Haiku 4.5 | $0.00004 | $0.00387 |
Grade A, and why
computational-experiments 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 26d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Computational Experiments
Lifecycle skill for algorithmic research projects where the code IS the scientific contribution.
Modes
| Mode | What it does | Phases |
|---|---|---|
| Scaffold | Create/audit package structure + algorithm skeleton | 1–2 |
| Experiment | Design and run pre-specified sweep campaigns | 1, 3–4 |
| Explore | Adaptive experiment loop: modify → run → evaluate → keep/discard | 1, 3E–4 |
| Autonomous | Parallel self-correcting sweep with sub-agents | 1, 3A–4 |
| Figures | Generate publication output from results | 1, 4 |
| Full | Complete pipeline | 1–5 |
Default: Full. Detect mode from user request or ask if ambiguous.
--scaffold Flag
Sets a stage progression template for the experiment campaign. Templates provide structured checklists and exit criteria for each stage.
| Scaffold | Stages | Best for |
|---|---|---|
standard |
Init → Tune → Creative → Ablate | Algorithm development, ML, simulation |
robustness |
Main spec → Alternatives → Placebo → Sensitivity | Causal inference, econometrics |
replication |
Exact → Our data → Extensions → Robustness | Replicate-and-extend papers |
Templates live in templates/experiments/. When a scaffold is active:
- Present the current stage's checklist before starting work
- Gate progression: don't move to the next stage until exit criteria are met
- Log stage transitions in the experiment breadcrumb
Default (no flag): user-defined stages (current behavior). Scaffold is a guide, not a cage — users can skip stages or reorder with explicit acknowledgment.
--budget Flag
Sets a campaign-level time budget in minutes for the entire experiment run. When set:
- Record start time at the beginning of Phase 3 (any variant)
- Check remaining budget before launching each new config, sweep batch, or explore iteration
- Soft stop when budget is exhausted: finish the current run, save all results collected so far, skip remaining configs
- Never hard-kill a running experiment mid-execution — always let the current run complete
What ships with it
10 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.
- references/algorithm-templates.md 17 KB
- references/autonomous-sweep.md 5.6 KB
- references/experiment-patterns.md 17 KB
- references/explore-loop.md 7.2 KB
- references/figure-recipes.md 13 KB
- references/multi-agent-infrastructure.md 14 KB
- references/multi-agent-patterns.md 8.6 KB
- references/multi-analyst-design.md 6.9 KB
- references/package-scaffold.md 7.7 KB
- references/python-econometrics.md 4.5 KB
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.
- 26d ago Changed e15aa98fd62e
- 1mo ago First seen · 276 lines · 43 tokens per session scan A 10e86e4fe258
computational-experiments is a skill published in the GitHub repository flonat/flonat-research (147 stars, last pushed 20d ago), licensed MIT. It adds 43 tokens to every session and 3,873 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 2026-09-03.
Other skills, from other repositories
academic-plotting
Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…
beamer-presentation
Create academic presentations in Beamer with professional themes.
latex-econ-model
Write and typeset economic models in LaTeX with proper notation.
academic-paper-writer
Draft economics papers with proper structure and academic style.
latex-tables
Generate publication-ready regression tables in LaTeX.
thesis-figure-skill
An academic-diagram skill for creating research-paper figures as TikZ/LaTeX code or draw.io XML. TikZ is code that embeds precisely into LaTeX papers, while draw.io XML creates diagrams editable in the draw.io app.