What is results-backfill?

A workflow for completing an empirical research paper after experiments have been run. It replaces draft placeholders with verified results, creates figures and tables, writes an abstract, refines the prose, and compiles the paper.

Use it to update a LaTeX paper from CSV experiment results, mark results as verified, generate paper assets, and produce a compiled PDF.

It removes the manual work of transferring experiment outputs into a paper and helps keep claims tied to actual result files. It requires an existing draft and completed experiments.

How yunshenwuchuxun/latex-paper-skills configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to yunshenwuchuxun/latex-paper-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/yunshenwuchuxun/latex-paper-skills/main/.codex/skills/results-backfill/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/yunshenwuchuxun/latex-paper-skills

Made for: Codex.

Wrote 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.

$agentmods badge for results-backfill$

README.md

[![agentmods](https://agentmods.dev/badge/skills/yunshenwuchuxun/latex-paper-skills/results-backfill/github.svg)](https://agentmods.dev/skills/yunshenwuchuxun/latex-paper-skills/results-backfill)

Your own site

<a href="https://agentmods.dev/skills/yunshenwuchuxun/latex-paper-skills/results-backfill"><img src="https://agentmods.dev/badge/skills/yunshenwuchuxun/latex-paper-skills/results-backfill/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.

$agentmods 80×15 button for results-backfill$

Your own site · 80×15

<a href="https://agentmods.dev/skills/yunshenwuchuxun/latex-paper-skills/results-backfill"><img src="https://agentmods.dev/badge/skills/yunshenwuchuxun/latex-paper-skills/results-backfill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,592 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00041	$0.01592
Opus 5	$0.00020	$0.00796
Sonnet 5	$0.00008	$0.00318
Haiku 4.5	$0.00004	$0.00159

Measured 12d ago against content hash b1c1767fe2d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

results-backfill 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/discover_results.py, scripts/generate_results_table.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.codex/skills/results-backfill/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Results Back-fill

Use this skill after empirical-paper-writer has produced a draft with placeholders and the user has run experiments outside the AI session.

When to Use

empirical-paper-writer has completed design + code + placeholder draft.
The user has run experiments in their configured conda environment.
paper/results/ contains new CSV / data files from completed experiments.

When NOT to Use

The paper draft does not yet exist (use empirical-paper-writer first).
Experiments have not been run yet.
The user only wants experiment design without paper completion.

Inputs

paper/main.tex (draft with placeholders)
paper/results/*.csv (experiment results)
notes/design/experiment-matrix.csv
issues/<timestamp>-<slug>.csv
brief/contribution-map.yaml
paper.config.yaml (runtime configuration)

Outputs

Updated main.tex with verified results, real figures/tables, factual claims
Updated issues CSV with Result_Status=verified and Status=DONE
Generated LaTeX input files under paper/results/
Drafted abstract (W0)
Refined prose (RF1)
Compiled main.pdf

Non-Negotiable Rules

No fabrication: Only use data from actual result files. Never invent numbers.
Verify before claiming: Only upgrade (hypothesis) to factual claim when CSV data confirms the result.
Bounded claims: Factual statements must include specific numbers from verified results (e.g., "reduces violations by 12.3%"), not vague improvements.
Dependency enforcement: Follow the same dependency rules as empirical-paper-writer — never mark DONE if dependencies are not DONE/SKIP.

Workflow

Phase 1: Results Discovery

Read paper.config.yaml for runtime configuration.
Scan paper/results/ for all CSV, JSON, and data files.
Read notes/design/experiment-matrix.csv to identify all planned experiments.
Match result files to experiment-matrix rows:
```
python3 scripts/discover_results.py --project-dir <paper_dir>
```
See references/backfill-workflow.md for naming conventions and the assets/result-file-template.csv schema.

If matches look correct, update the matrix in-place:

python3 scripts/discover_results.py --project-dir <paper_dir> --update-status

Read the issues CSV and update Result_Status for matched experiment issues (E5-E8).

Read the full file on GitHub · 157 lines

Files

What ships with it

4 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.

Changes

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.

12d ago First seen · 157 lines · 41 tokens per session scan A b1c1767fe2d4

Subscribe to this mod's changes

results-backfill is a skill published in the GitHub repository yunshenwuchuxun/latex-paper-skills (259 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,592 once invoked, about $0.0002 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 2026-08-30.

Scientific Writing and docs

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…

anthropics/knowledge-work-plugins · 123 tokens

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.

K-Dense-AI/scientific-agent-skills · 42 tokens

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…

K-Dense-AI/scientific-agent-skills · 83 tokens

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.

K-Dense-AI/scientific-agent-skills · 68 tokens

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.

davila7/claude-code-templates · 43 tokens

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…

maziyarpanahi/openmed · 205 tokens

latex-paper-skills: Skill for Codex