Borrowing it
Nothing to install: this file belongs to pachterlab/paperpush. 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/pachterlab/paperpush/main/AGENTS.mdgit clone --depth 1 https://github.com/pachterlab/paperpushWrote 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/instructions/pachterlab/paperpush/agents-md)<a href="https://agentmods.dev/instructions/pachterlab/paperpush/agents-md"><img src="https://agentmods.dev/badge/instructions/pachterlab/paperpush/agents-md/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/instructions/pachterlab/paperpush/agents-md"><img src="https://agentmods.dev/badge/instructions/pachterlab/paperpush/agents-md.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 | $0.06156 | $0.06156 |
| Opus 5.5 | $0.02462 | $0.02462 |
| Sonnet 5.5 | $0.01231 | $0.01231 |
| Haiku 4.5 | $0.00616 | $0.00616 |
Grade A, and why
paperpush AGENTS.md 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 today.
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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for any AI agent (Codex, Claude, or otherwise) that decides to use
paperpush to submit a manuscript to a venue - a journal, preprint server, or conference -
on a user's behalf.
Skills: which one to use, and when
paperpush ships its workflows as agent skills (skills/<name>/SKILL.md). If
yours are installed, use the matching skill instead of working from this file
alone: it holds the same contract, step by step. If you can't load skills,
open the SKILL.md and follow it as written.
| Skill | What it does | Call it when the user... |
|---|---|---|
paperpush-prepare-submission |
The whole flow: checks the login, finds or creates the .sub, runs autofill, runs validate, then hands off to paperpush-submit. |
asks to prepare, get ready, or submit a manuscript to a venue, and has not named a single step. Start here when in doubt. |
paperpush-autofill |
Reads the manuscript directory, writes values.json, and applies it with paperpush autofill --engine manual. Leaves never fields for the author. |
wants a .sub filled from their files, and nothing else yet. |
paperpush-validate |
Runs paperpush validate, then does the checks that need a reader (lettering in raster figures, panel labels, free-text guideline rules, .sub vs manuscript) through --ai-tasks / --ai-results. Optionally saves the report. |
asks whether a manuscript or .sub is ready, meets a venue's guidelines, or passes validation, or wants the AI checks or a saved report. |
paperpush-submit |
Takes a filled .sub to the portal: re-checks the login (paperpush login <venue> --check), confirms with the user, runs submit (or submit(skip_validate=true) when asked to skip validation), and follows the run, handing a failed step to paperpush-portal-debug. Stops before the final submit. |
has a .sub ready and wants the portal filled in, e.g. "fill out the submission portal to nature", optionally "skip validation". |
paperpush-portal-debug |
Gets a stalled paperpush submit run past the failing step on the live page (submit_page / submit_act / submit_resume), logs every runner change it needs, and puts those changes into the runner with a test when working in a source checkout. Never sends the submission. |
reports that submit is stuck, failed at a step, or hit a portal that changed. Also use it yourself whenever submit_status shows recovery.paused. |
paperpush-add-venue-validate |
Reads a venue's author guidelines and records them in manuscript_requirements.json, and its basic submission fields in submission_forms.json, through a venue file and paperpush add-venue. For an existing venue, re-reads the pages and updates what changed. |
wants a venue that validate can check against, or wants a venue's guidelines, limits, or rules added or refreshed. Contributor skill: needs a clone of the repo. |
paperpush-add-venue |
Full submit support: a Venue class with Playwright login() / submit(), the portal's fields, a sample .sub with generated documents, unit tests, and a live run that stops before the final submit. For an existing runner, runs its tests and fixes what fails. Has the user create an account and run paperpush login rather than handing over a password. |
wants to submit to a venue paperpush can't submit to yet, or reports that a venue's runner or tests are broken. Runs paperpush-add-venue-validate first if the venue has no guidelines entry yet. Contributor skill: needs a clone of the repo. |
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.
- today Changed · +15 lines · +377 tokens per session 6830379fe3d1
- yesterday Changed · +39 lines · +1,046 tokens per session 4830320b9c53
- 2d ago Changed · +59 lines · +971 tokens per session 862845b78e92
- 4d ago Changed · +4 tokens per session 03c276108ee4
- 10d ago Changed · +33 lines · +481 tokens per session 7ca8e2f74443
- 1mo ago Changed · +46 lines · +750 tokens per session ae379c45e068
- 1mo ago Changed · +14 lines · +199 tokens per session adda82f74f27
- 2mo ago First seen · 190 lines · 2,328 tokens per session scan A c5ce57ac2962
paperpush AGENTS.md is an instructions file published in the GitHub repository pachterlab/paperpush (210 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 6,156 tokens to every session, about $0.0246 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 2026-08-30.
paperpush AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| paperpush AGENTS.mdpachterlab/paperpush | Instructions file | 210 | yesterday | BSD-2-Clause | A | 6,156 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |