agentmods.dev

paper

paper is a command for coding agents from koolamusic/claudefiles. It costs 54 tokens per session (2,708 once invoked), scanned A, original, MIT.

A command that turns a real engineering discovery, finding, or innovation into a short single-file HTML paper. It organizes what happened, the evidence for it, and what the evidence can safely support.

In plain words
What is it for?
Use it to document an engineering result as an innovation, discovery, or finding, with an evidence inventory and an optional publishing step.
Why use it?
It prevents weak claims and unsupported conclusions from being presented as established facts. Publishing is kept separate from drafting.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the jira plugin — 13 commands, 9 agents shipped together

not rated 132 5d ago A scan 54 tokens original MIT
View the source file koolamusic/claudefiles
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 commands/koolamusic/claudefiles/paper
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install jira, the plugin that ships this one along with the rest of its 13 commands, 9 agents.

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 paper

README.md
[![agentmods](https://agentmods.dev/badge/commands/koolamusic/claudefiles/paper.svg)](https://agentmods.dev/commands/koolamusic/claudefiles/paper)
Your own site
<a href="https://agentmods.dev/commands/koolamusic/claudefiles/paper"><img src="https://agentmods.dev/badge/commands/koolamusic/claudefiles/paper.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,708 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.

ModelPer sessionOnce invoked
Fable 5 $0.00054 $0.02708
Opus 5 $0.00027 $0.01354
Sonnet 5 $0.00011 $0.00542
Haiku 4.5 $0.00005 $0.00271

Measured 4d ago against content hash 28d105aa6def, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paper 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.

plugins/jira/commands/paper.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Turn a real engineering finding, discovery, or innovation into a short, rigorous, single-file HTML paper — evidence-gated internally, magazine-lean on the page. This command runs the house master prompt's discipline (evidence before prose, claim strength matched to evidence strength, stop when the evidence doesn't support the claim) but skips its heavier academic apparatus (no Abstract/Keywords/Related-Work-as-sections, no external literature search) because nothing in this house's paper corpus uses it. If a paper genuinely needs to cite external prior work, the user supplies verified sources — this command does not go looking for them.

Parse the input

$ARGUMENTS:

  • Description (positional, required unless --publish is given): freeform text — what was built, changed, tested, or discovered, and why it mattered. If empty, use AskUserQuestion to collect it in one question (what happened / why it mattered / roughly when).
  • --category innovation|discovery|finding (optional): skip the categorization step if given.
  • --out <dir> (optional): override the resolved artifacts directory.
  • --publish <slug>: skip straight to the Publish gate (step 8) for an existing artifacts/drafts/<slug>.html — no redrafting, no re-review. Use this after hand-editing a draft.

Resolve the artifacts directory

  1. --out <dir> wins if given.
  2. Else, if .jira is a symlink (studio-managed project): studio_root=$(dirname "$(readlink -f .jira)"), use $studio_root/artifacts.
  3. Else: <repo-root>/artifacts.
  4. Ensure <artifacts-dir>/drafts/ exists (mkdir -p).
  5. If <artifacts-dir>/index.html doesn't exist, bootstrap it from ${CLAUDE_PLUGIN_ROOT}/templates/paper/index.html — ask the user for a one-line site title and intro via AskUserQuestion if not inferable from the repo name and README.

If --publish <slug> was given, skip to step 8 now.

Steps

  1. Evidence inventory (internal — not a user-facing checkpoint).

    Read the user's description. Then actively hunt for supporting evidence:

    • git log, git show <sha>, git log --grep for named or implied commits
    • gh pr list / gh pr view if a PR is referenced and gh is available
    • .jira/sprints/*/RESEARCH.md, EXECUTION.md, VERIFICATION.md, RETRO.md for anything matching the described work
    • .warden/logs/, .warden/runs/ for measured run output, if present
    • migration files, config diffs, benchmark output the user pasted inline

Read the full file on GitHub · 117 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. 4d ago First seen · 117 lines · 54 tokens per session scan A 28d105aa6def

Subscribe to this mod's changes

paper is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 5d ago), licensed MIT. It adds 54 tokens to every session and 2,708 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 2026-08-30.

ScientificWriting and docs
Related

Other commands, from other repositories

me-figure-discussion

Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.

hanhuark/mechanical-engineering-research-skill · 21 tokens

master_analysis

Run comprehensive 5-phase analysis across labs, genetics, and protocols.

gtr36/personal-health-graph · 13 tokens

run-panguweather

Guide the user through running PanguWeather end-to-end on an AMD cluster.

AMDResearch/ai4science-studio · 0 tokens

render-figures

Compile all .tex and .typ figure files in a directory.

braininahat/brains-in-a-hat · 17 tokens

diff

Quantitative volume comparison between a CadQuery model and a reference STEP file.

fa-mc/vibe-cading · 14 tokens

arg-diagram

ARG academic-paper diagram mode — standalone structural & conceptual diagram generation.

Masqiller/ARG-RESEARCHER-V4.1 · 14 tokens