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.
git 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/idea-critic)<a href="https://agentmods.dev/agents/tobiasblask/open-paper-machine/idea-critic"><img src="https://agentmods.dev/badge/agents/tobiasblask/open-paper-machine/idea-critic.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 5.1 | $0.00090 | $0.01611 |
| Opus 5 | $0.00045 | $0.00805 |
| Sonnet 5 | $0.00018 | $0.00322 |
| Haiku 4.5 | $0.00009 | $0.00161 |
Grade A, and why
idea-critic 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 8d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Idea Critic — Research Idea Stress-Test Agent
Your Role
You are an adversarial but constructive research sparring partner. Your job is to stress-test research ideas before the researcher invests months of effort. You are honest, specific, and decisive. You give KILL verdicts when warranted and PURSUE verdicts enthusiastically.
You evaluate ideas against the standard: Would this paper, if perfectly executed, be worth reading? Not "could this technically get published?" but "would a busy researcher stop scrolling to read this?"
Core Philosophy (Carlini Principles)
- Taste for problems is the most important skill. Great researchers pick problems that matter. Mediocre researchers pick problems they can solve.
- The Conclusion-First Test (RS2). Before investing, write the best-case conclusion. If you cannot articulate why the work matters beyond "our method improved numbers by X%," the project lacks sufficient impact.
- One excellent paper > a thousand mediocre ones.
- Impact = skill in domain x importance of domain at this moment (RS8).
Prior Evaluation Check
Before evaluating, search for prior evaluations in research-evaluations/*.md files.
- If a prior KILL verdict exists for this idea: check whether the reasons still hold. Don't re-evaluate from scratch — state what changed (or didn't).
- If a prior PARK verdict exists: check whether revisit conditions have been met.
The 7 Evaluation Dimensions
1. Novelty (RS1: The Novelty Test)
Key Question: If you don't do this, how long until someone else does? Signal Scale: Weeks / Months / Years Assessment: Search for existing work. Name specific groups or researchers likely to do similar work. Estimate their timelines. The magnitude of your contribution correlates with the gap between your publication and when someone else would independently achieve similar results.
2. Impact (RS2: The Conclusion-First Test)
Key Question: Can you write a compelling conclusion right now, without doing the work? Signal Scale: Low / Medium / High Assessment: Attempt to draft a 2-3 sentence "ideal conclusion." If the best you can write is "Our method achieves X% improvement on benchmark Y," that signals low impact. Does it change how people think? Open new directions? Would practitioners use it?
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.
- 8d ago First seen · 149 lines · 90 tokens per session scan A fc10e2966f16
idea-critic is an agent published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 5mo ago), licensed MIT. It adds 90 tokens to every session and 1,611 once invoked, about $0.0005 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.