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 evoelsewhere/evoflux --skill super-researchgit clone --depth 1 https://github.com/evoelsewhere/evofluxWrote 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/evoelsewhere/evoflux/super-research)<a href="https://agentmods.dev/skills/evoelsewhere/evoflux/super-research"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/super-research/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/evoelsewhere/evoflux/super-research"><img src="https://agentmods.dev/badge/skills/evoelsewhere/evoflux/super-research.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 | $0.00102 | $0.02171 |
| Opus 5 | $0.00051 | $0.01086 |
| Sonnet 5 | $0.00020 | $0.00434 |
| Haiku 4.5 | $0.00010 | $0.00217 |
Grade A, and why
super-research 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 3d 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
89% identical to super-research — 2 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Research
You are about to become an autonomous researcher. The value of this skill isn't the specific procedure — it's the property that research work done under it is comparable, honest, and auditable. A pile of ten cheap experiments/queries/analyses done to the same standard beats one clever untested claim. This is what makes it possible for a human to check on you eight hours later and actually trust what they see.
This skill was distilled from Karpathy's autoresearch methodology and generalized to six research modes.
Shared discipline (all modes)
Every mode operates under the same five rules. Read them before you branch into a mode.
-
State a contract before you begin. Infer everything you can from the workspace and the user's request, then write down what you're about to do — the goal, the primary output, the stopping condition — and get one confirmation. This is your last question. After confirmation you are autonomous.
-
Establish a baseline as your first artifact. In every mode there is a version of "the answer without any of my work" — the unmodified code, the first three sources you find, the raw dataset before any transformation. Record it first. Without a baseline, "better" and "significant" are meaningless.
-
Every step is logged, in a machine-readable file, including failures. A tab-separated log (TSV, not CSV — descriptions contain commas) with a header row and one row per attempt. Failed attempts get logged with a
crash/dead-end/inconclusivestatus. Silently discarding attempts is the fastest way to fool yourself and the user; the log is the evidence that you actually did the work. -
Never pause to ask permission mid-loop. Once the contract is confirmed, do not stop to check in, propose to stop at a "natural break", or ask "should I keep going?". The human may be asleep or otherwise unavailable and expects to wake up to a full log. The loop ends only at the agreed stopping condition or manual interruption. This is the single most common failure mode of autonomous runs.
What ships with it
29 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.
- agents/evoflux.yaml 282 B
- evals/evals.json 12 KB
- evals/toy_bench/candidates/cleaner_a.py 228 B runs code
- evals/toy_bench/candidates/cleaner_b.py 434 B runs code
- evals/toy_bench/candidates/cleaner_c.py 362 B runs code
- evals/toy_bench/README.md 994 B
- evals/toy_bench/run_case.sh 815 B runs code
- evals/toy_dataset/dataset.csv 45 KB
- evals/toy_dataset/generate.py 1.4 KB runs code
- evals/toy_dataset/README.md 843 B
- evals/toy_pipeline/pipeline.py 2.2 KB runs code
- evals/toy_pipeline/README.md 2.1 KB
- evals/toy_regression/README.md 1.4 KB
- evals/toy_regression/setup.sh 3.4 KB runs code
- evals/toy_repo/README.md 449 B
- evals/toy_repo/run.py 1.4 KB runs code
- evals/trigger-cases.json 916 B
- references/ablation-study.md 8.1 KB
- references/api-cheatsheet.md 3.0 KB
- references/benchmark-comparison.md 5.5 KB
- references/experiment-loop.md 5.2 KB
- references/paper-reproduction.md 7.8 KB
- references/paper-writing.md 8.8 KB
- references/quant-analysis.md 6.7 KB
- references/root-cause.md 8.2 KB
- references/topic-survey.md 8.0 KB
- scripts/fetch_paper.py 7.3 KB runs code
- scripts/paper_search.py 7.3 KB runs code
- scripts/verify_citation.py 9.0 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.
- 3d ago First seen · 91 lines · 102 tokens per session scan A 799b940477e6
super-research is a skill published in the GitHub repository evoelsewhere/evoflux (7 stars, last pushed today), licensed Apache-2.0. It adds 102 tokens to every session and 2,171 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to super-research, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
cuopt-numerical-optimization-formulation
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
earth2studio-create-datasource
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for fetching data with existing sources, model inference, or installation tasks.
earth2studio-data-fetch
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
ai-scaling-laws
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or over-training tradeoffs.