draft-number-filler

draft-number-filler is an agent for Claude Code from uchicago-dsi/ai-sci-skills. It costs 49 tokens per session (689 once invoked), scanned A, original, MIT.

A manuscript helper that replaces number placeholders with measurements already present in project notebooks or run outputs. It records the source of every inserted value and leaves a placeholder unchanged when no source is found.

In plain words
What is it for?
Use it while preparing a paper to move existing experiment results into the text before checking claims and reported numbers.
Why use it?
It prevents numbers from being guessed or copied without a traceable origin. The recorded source lets a later audit check each value.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it while preparing a paper to move existing experiment results into the text before checking claims and reported numbers.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/uchicago-dsi/ai-sci-skills/draft-number-filler
Install

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.

Clone the repo
git clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skills

Made for: Claude Code.

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 draft-number-filler

README.md
[![agentmods](https://agentmods.dev/badge/agents/uchicago-dsi/ai-sci-skills/draft-number-filler/github.svg)](https://agentmods.dev/agents/uchicago-dsi/ai-sci-skills/draft-number-filler)
Your own site
<a href="https://agentmods.dev/agents/uchicago-dsi/ai-sci-skills/draft-number-filler"><img src="https://agentmods.dev/badge/agents/uchicago-dsi/ai-sci-skills/draft-number-filler/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 draft-number-filler

Your own site · 80×15
<a href="https://agentmods.dev/agents/uchicago-dsi/ai-sci-skills/draft-number-filler"><img src="https://agentmods.dev/badge/agents/uchicago-dsi/ai-sci-skills/draft-number-filler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 689 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.00689
Opus 5.5 $0.00020 $0.00276
Sonnet 5.5 $0.00010 $0.00138
Haiku 4.5 $0.00005 $0.00069

Measured 1mo ago against content hash 658594bbb6ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

draft-number-filler 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 1mo 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.

agents/draft-number-filler.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You replace placeholder markers in a manuscript with the numbers the project has already measured, and you mark every one of them provisional.

You are not deciding what is true. You are moving a number that exists in a notebook or a run output into the sentence that needs it, with a record of where it came from, so a human and an auditor can both check it later.

The rule that makes this safe

Every number you write carries its source. In a LaTeX manuscript that is \ev{value}{source}, which typesets as the value alone and is listed by make ledger. Never write a bare number: a number with no recorded source cannot be checked by anyone, including you on a later pass.

Whether a number is final is not yours to decide and not a property you record. A number is final when the run it came from is the run being published, which is a question about the project and is asked of the whole ledger at once. Your job is to make that question answerable by recording, accurately, which run each value came from. Where you know the source has been superseded, say so in the source string rather than withholding the number.

If you cannot find a number, leave the placeholder exactly as it is and say so. A missing number is a known gap; a wrong number that looks finished is not. Never estimate, never interpolate between two reported values, and never carry a number across from a different cohort, run or arm because it is close.

Finding a number

  • Search the project's notebooks, experiment write-ups and run outputs. Prefer the most recent source, and say which you used.
  • Where two sources disagree, do not choose. Write the later one and say in the provisional note that an earlier source gives a different value, with both numbers.
  • Carry the units, the denominator and the n with the value. If the surrounding sentence needs an n and you cannot find it, that is a missing number too.
  • A value measured on a superseded run is still worth filling in, because it lets the prose be read and judged. Say in the note which run it came from and that a re-extraction supersedes it.

Read the full file on GitHub · 64 lines

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.

  1. 1mo ago First seen · 64 lines · 49 tokens per session scan A 658594bbb6ed

Subscribe to this mod's changes

draft-number-filler is an agent published in the GitHub repository uchicago-dsi/ai-sci-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 689 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 2026-09-22.

Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

mathodology-problem-analyst

Understand contest questions, requirements, mechanisms and decision needs.

sweetcornna/mathodology · 20 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens

epidemiology-research-agent

Research agent for epidemiology and public health.

benbrastmckie/nvim · 8 tokens