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 replication-packagegit 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/replication-package)<a href="https://agentmods.dev/skills/flonat/flonat-research/replication-package"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/replication-package/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/replication-package"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/replication-package.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 151 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00052 | $0.02383 |
| Opus 5 | $0.00026 | $0.01192 |
| Sonnet 5 | $0.00010 | $0.00477 |
| Haiku 4.5 | $0.00005 | $0.00238 |
Grade A, and why
replication-package 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 8d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Replication Package — Assemble, Anonymize, and Audit
Build publication-ready replication packages, optionally anonymize for double-blind review, or audit an existing package for reproducibility. The original project is never modified.
Modes
| Mode | What it does | Use case |
|---|---|---|
| Assemble | Clean copy + AI trace removal + AEA-style README | Sharing, Zenodo deposit, journal supplementary |
| Blind | Everything in Assemble + identity anonymization | Double-blind conference/journal submission |
| Audit | Read-only 11-check reproducibility validation | Pre-deposit quality gate, self-check |
Default mode: Assemble. Infer Blind if the user says "anonymize", "double-blind", or "blind review". Infer Audit if the user says "audit", "check reproducibility", or "validate package".
When to Use
- Submitting supplementary materials or replication files to a journal
- Depositing a package on Zenodo, Dataverse, or ICPSR
- Sharing a project repo publicly (GitHub, institutional repository)
- Preparing for double-blind submission (Blind mode)
- Self-checking reproducibility before deposit (Audit mode)
When NOT to Use
- Quick one-off cleanup of a single file — do it manually
- Removing a single AI artifact — just delete it directly
- Projects with no empirical or computational component
Critical Rules
- Never modify the original project. All work happens on a copy in a sibling folder.
- Dry-run mandatory. Always show what will be removed/changed and get user confirmation before any deletions.
- Binary files are never modified. Warn the user to manually check PDFs (Document Properties), images (EXIF data), and datasets for embedded metadata.
- Self-citations are always interactive. Never auto-remove or auto-anonymize a citation. Flag each potential self-citation and let the user decide per citation. In Blind mode, surface every self-citation against the loaded submission author list and require a per-citation decision (third-person OK / blind the entry). When the cited paper's author list is a subset of the submission's, third-person is structurally insufficient and the bib entry MUST be blinded — see
_shared/double-blind-anonymity-checklist.md§P4–P5. - Resolve symlinks. Use
rsync -aLso symlinked content (e.g., Overleafpaper/symlinks) becomes real files in the copy. - Preserve compilability. The output must still compile/run — only infrastructure and identity are removed, not project functionality.
- Blind mode runs the structured-metadata field check (A2) before reporting clean.
pyproject.toml[project] authors,package.jsonauthor/contributors,Cargo.toml[package] authors,CITATION.cff,LICENSEholder, etc. — see_shared/double-blind-anonymity-checklist.md§"Structured-metadata field check (A2)" for the full target list. This was the CCS 2026 #1328 desk-reject trigger and is now non-skippable.
What ships with it
13 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/aea-readme-template.md 5.4 KB
- references/anonymization-patterns.md 3.8 KB
- references/assemble-workflow.md 10.0 KB
- references/audit-rubric.md 11 KB
- references/audit-workflow.md 3.8 KB
- references/blind-workflow.md 4.0 KB
- references/deposit-checklist.md 6.6 KB
- references/expected-values-schema.md 4.8 KB
- references/figure-table-crosswalk.md 3.7 KB
- references/logging-skeletons.md 3.7 KB
- references/release-readiness-checklist.md 3.1 KB
- references/report-template.md 2.1 KB
- references/rules.dropboxignore 677 B
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.
- 8d ago First seen · 166 lines · 52 tokens per session scan A 1d6ddc365310
replication-package is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 52 tokens to every session and 2,383 once invoked, about $0.0003 per session on Opus 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
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.
sync-wb-nb
Propagate a change made in a Wolfbook .wb notebook into the paired .nb notebook so the two stay identical. Use immediately after every .wb edit.
wolfram-headless
Run heavy Wolfram Language (wolframscript) computations from Claude Code reliably, and diagnose the misleading "The product exited because of a license error". Use whenever invoking wolframscript on a non-trivial computation, when a wolframscript job dies with a "license error" despite a valid license, or when Wolfram…
cross-validate
Format a result, derivation, or numerical value for independent verification by a second model. Use when you want a cross-check on an important or contested result.
verify-citation
Confirm a paper actually exists (arXiv / Semantic Scholar / OpenAlex) before citing it. Use before writing any new citation.