Formatting instructions for papers submitted to COLM, the Conference on Language Modeling. They cover setting up, moving to, or fixing the COLM paper template and related submission checks.

Use it when preparing a COLM paper, adapting an existing paper to the COLM template, or fixing template and compilation problems.

It helps make a research paper follow the conference’s required layout and preparation process. It also directs the writer to shared guidance for clear writing, citations, and review readiness.

colm — Skill for Claude Code and Codex by nanoAgentTeam: Formatting instructions for papers submitted to COLM, the Conference…

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.

agentmods

npx agentmods add skills/nanoagentteam/research-claw/colm

Any agent

npx skills add nanoAgentTeam/research-claw --skill colm

Clone the repo

git clone --depth 1 https://github.com/nanoAgentTeam/research-claw

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nanoagentteam/research-claw/colm.svg)](https://agentmods.dev/skills/nanoagentteam/research-claw/colm)

Your own site

<a href="https://agentmods.dev/skills/nanoagentteam/research-claw/colm"><img src="https://agentmods.dev/badge/skills/nanoagentteam/research-claw/colm.svg" alt="Measured on agentmods" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,235 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00032	$0.02235
Opus 5	$0.00016	$0.01118
Sonnet 5	$0.00006	$0.00447
Haiku 4.5	$0.00003	$0.00224

Measured 4d ago against content hash 650fc18ff3ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

colm 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 4d 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.

config/.skills/colm/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[SKILL: COLM PAPER FORMAT]

Activate when: user mentions COLM, Conference on Language Modeling, or asks to use/fix the COLM template.

Execution Protocol

After this skill is activated, select the matching scenario based on user intent.

Shared Common Workflow

Before venue-specific template steps, also load and follow ml-paper-writing skill.

At minimum, apply these shared references:

writing-guide.md (narrative and clarity)
citation-workflow.md (verified citations; no hallucinations)
reviewer-guidelines.md (reviewer-facing quality checks)
checklists.md (pre-submission gates)

Built-in template: templates/colm2025/ (referred to as TEMPLATES_DIR below), targeting COLM 2025. Contents: colm2025_conference.sty, colm2025_conference.bst, colm2025_conference.tex, colm2025_conference.bib, colm2025_conference.pdf, fancyhdr.sty, natbib.sty, math_commands.tex.

Pre-step: Year Confirmation & Template Acquisition

This step MUST be completed before any scenario below.

Confirm target year and stage (submission, preprint, or final). Default to latest available year if user does not specify.
Check whether TEMPLATES_DIR exists and includes required files: colm2025_conference.sty, colm2025_conference.bst, colm2025_conference.tex, fancyhdr.sty, natbib.sty.
Use local built-in template only when BOTH conditions hold:
- target year = 2025
- files in TEMPLATES_DIR are complete
If either condition fails (target year is not 2025 OR local template files are missing/incomplete), execute this workflow:
- Inform user local built-in template is unavailable or year-mismatched
- Open official COLM site: http://www.colmweb.org/
- Find target-year CFP/submission page and locate "Author Kit", "Style Files", or template links
- If official site has no direct files, check target-year OpenReview submission page for template links
- Download official target-year template package (.zip or repository snapshot)
- Unzip downloaded files directly into <PROJECT_CORE>.
- Continue all remaining steps with downloaded year-specific filenames
Confirm paper type/page policy from current CFP before edits (common baseline in recent years: main text up to 9 pages, references unlimited).
Filename substitution rule for all steps below:
- Treat colm2025_conference in commands/examples as a placeholder for the resolved style basename from the selected .sty file.
- Example: if the downloaded file is colm2026_conference.sty, replace colm2025_conference with colm2026_conference in \\usepackage, \\bibliographystyle, copy commands, and checks.

Read the full file on GitHub · 211 lines

Files

What ships with it

9 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.

4d ago First seen · 211 lines · 32 tokens per session scan A 650fc18ff3ff

Subscribe to this mod's changes

colm is a skill published in the GitHub repository nanoAgentTeam/research-claw (292 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 2,235 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.

Autonomous Agents LLM Scientific Writing and docs academic-writing ai-agent arxiv feishu-bot

generate-plot

Generate a publication-quality statistical plot from a data file using PaperBanana.

llmsresearch/paperbanana · 0 tokens

neuroarxiv

Grounds a coding agent's architecture decisions in real arXiv prior art before it builds something new. Reads arXiv category-wise via real HTTP fetch, spawns parallel isolated reads across the papers found, scores/clusters them, then converges on ONE recommended path with citations, a first step, and known prior-art…

UditAkhourii/neuroarxiv · 162 tokens

arxiv

Search arXiv papers by keyword, author, category, or ID.

mateaix/mateclaw · 18 tokens

arxiv-fetch

Fetch the latest arXiv papers and generate an on-demand digest. Use when the user asks to fetch/check today's (or the latest) arXiv papers, find new papers on a topic, or generate an ad-hoc arXiv digest. The agent judges relevance itself — no API keys needed.

yang3kc/daily_arxiv_digest · 66 tokens

paper-read

Read, analyze, and extract knowledge from academic papers. Handles PDFs and arXiv links. Produces structured summaries, identifies core contributions, evaluates methodology, and enables cross-paper comparison.

Calix-L/awesome-latex-skills · 40 tokens

overleaf

Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.

aloth/overleaf-skill · 62 tokens