Borrowing it
Nothing to install: this file belongs to fbabelle/PrettySeriousResearcher. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fbabelle/PrettySeriousResearcher/main/.claude/skills/research-provenance/SKILL.mdgit clone --depth 1 https://github.com/fbabelle/PrettySeriousResearcherWrote 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/fbabelle/prettyseriousresearcher/research-provenance)<a href="https://agentmods.dev/skills/fbabelle/prettyseriousresearcher/research-provenance"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-provenance/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/fbabelle/prettyseriousresearcher/research-provenance"><img src="https://agentmods.dev/badge/skills/fbabelle/prettyseriousresearcher/research-provenance.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 | $0.00054 | $0.01199 |
| Opus 5 | $0.00027 | $0.00600 |
| Sonnet 5 | $0.00011 | $0.00240 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
research-provenance 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research provenance — the results-integrity gate
LLM-authored papers invent plausible-looking numbers the same way they invent citations: a Sharpe of 2.1 that never came out of a run, a table cell nudged to look better, a figure regenerated from stale data. This skill makes that impossible to ship by forcing every reported result to resolve to a logged run artifact before it can enter the draft — the exact discipline research-references applies to citations, applied to results. In AI+Finance, fabricated/overfit numbers are the #1 failure mode, so this is a first-class gate, not a nicety.
The rule
A number, table cell, or figure that cannot be traced to a logged artifact in runs/ does not go in the paper. Every reported value must resolve to a run keyed by config-hash → metric (the instrumented output research-experiments writes). Placeholders, hand-typed values, and hand-edited figures are defects, not results.
When it fires
- At results-capture (Phase 3) — as
research-experimentspersists outputs, reconcile each headline number to its producing run so provenance is captured while the run context is fresh. - At the Phase-4 exit — a full sweep of the draft: every table cell, every in-text statistic, every figure traces back, or it is flagged.
- Its output is a required input to the
research-mock-reviewpacket.
The protocol
- Enumerate every reported quantity in the draft (abstract stats, table cells, figure data, in-text numbers).
- Resolve each to an artifact — the
runs/record (config-hash, seed, metric) that produced it. Regenerate figures fromruns/via theresearch-visualsfigures-as-code pipeline so a figure is its artifact, not a pasted bitmap. - Assign a verdict: RESOLVED (traces cleanly), STALE (artifact exists but predates the current config — rerun), or UNRESOLVED (no artifact / placeholder / hand-edited → must fix or remove).
- Surface only the exceptions. Emit a reconciliation table, but only STALE/UNRESOLVED rows need the user's attention — so the user never hunts the whole draft for a fabricated number (that diagnosis is done for them).
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.
- 10d ago First seen · 59 lines · 54 tokens per session scan A f7a8326e73c4
research-provenance is a skill published in the GitHub repository fbabelle/PrettySeriousResearcher (2 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 1,199 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 2026-08-31.
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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…