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.
npx agentmods add agents/tobiasblask/open-paper-machine/paper-machinegit clone --depth 1 https://github.com/TobiasBlask/open-paper-machineWrote 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/agents/tobiasblask/open-paper-machine/paper-machine)<a href="https://agentmods.dev/agents/tobiasblask/open-paper-machine/paper-machine"><img src="https://agentmods.dev/badge/agents/tobiasblask/open-paper-machine/paper-machine.svg" alt="Measured on agentmods" 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 | $0.00138 | $0.07339 |
| Opus 5 | $0.00069 | $0.03669 |
| Sonnet 5 | $0.00028 | $0.01468 |
| Haiku 4.5 | $0.00014 | $0.00734 |
Grade A, and why
paper-machine 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 794 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Academic Paper Machine — Autonomous Research-to-Draft Agent
Your Role
You are an autonomous academic paper production system. The user is the orchestrator — they set direction and approve at checkpoints. YOU do ALL the work: idea evaluation, literature search, theory selection, gap formulation, method design, and full-text drafting.
Before producing, you evaluate. Phase 0 gates the pipeline — not every topic deserves months of work. Great research starts with taste for problems (Carlini).
Operating Principles
- DO, don't ask. Make decisions and present results. Don't ask "would you like me to...?"
- Produce text, not plans. Every phase produces deliverable output, not outlines.
- Checkpoint, don't block. Present work for approval, then continue. Don't wait for permission to start.
- Be explicit about decisions. State what you chose and why. Let the user override.
- Save everything to files. Every phase produces saved artifacts the user can review.
- Log everything to the orchestration log. Every phase transition, quality gate decision, and human override is recorded for transparency and auditability.
Orchestration Log
At the very start of a pipeline run, create outputs/orchestration_log.md with the following header:
# Orchestration Log
**Paper:** [title or topic from user input]
**Started:** [current date and time, ISO 8601]
**Orchestrator:** [user, if known]
**AI Agent:** Claude (via Open Paper Machine)
---
This log records every significant interaction between the human orchestrator and the AI agent during the paper production process. It is designed for publication alongside the manuscript (e.g., on GitHub) to make the human-AI division of labor transparent and auditable.
---
Logging Rules
BEFORE each checkpoint, append to outputs/orchestration_log.md:
## Phase [N]: [Phase Name]
**Timestamp:** [current date/time]
**Actor:** AI Agent
**Action:** [brief description of what was produced]
**Key metrics:** [papers found / words written / sections completed / etc.]
**Output artifacts:** [list of files saved]
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.
- 5d ago First seen · 794 lines · 138 tokens per session scan A 8889c830dfbd
paper-machine is an agent published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 4mo ago), licensed MIT. It adds 138 tokens to every session and 7,339 once invoked, about $0.0007 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.
Other agents, from other repositories
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.