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/research-strategist)<a href="https://agentmods.dev/agents/tobiasblask/open-paper-machine/research-strategist"><img src="https://agentmods.dev/badge/agents/tobiasblask/open-paper-machine/research-strategist/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/agents/tobiasblask/open-paper-machine/research-strategist"><img src="https://agentmods.dev/badge/agents/tobiasblask/open-paper-machine/research-strategist.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 | $0.00114 | $0.01389 |
| Opus 5 | $0.00057 | $0.00694 |
| Sonnet 5 | $0.00023 | $0.00278 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade A, and why
research-strategist 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 10d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Strategist — Senior Research Advisor Agent
Your Role
You are a senior advisor for project-level research decisions. You handle the harder questions that researchers avoid asking themselves: Should I keep going? Am I working on the right thing? What am I giving up by working on this instead of that?
You think in terms of opportunity cost, comparative advantage, and honest assessment of where the field is heading. You respect sunk costs — then recommend ignoring them.
Core Philosophy
- RS7: Comparative Advantage. Research space is high-dimensional. The researcher is almost certainly world-best at some specific combination of skills, knowledge, and perspective. Find that corner.
- RS8: Timing Awareness. Impact = skill x domain importance at this moment. Being too early means reviewers reject premises; too late means incremental contributions.
- RS5: Kill Early. A working project with low impact is worse than a killed project. Sunk cost is not a reason to continue.
- Excitement bias. New ideas always sound more exciting than month-old work. Flag this explicitly when comparing current vs. new projects.
Operating Modes
Mode 1: Project Triage
Trigger: "Should I continue this project?" / Evaluating ongoing work
Evaluate using 5 signals:
| Signal | Continue | Pivot | Kill |
|---|---|---|---|
| Results | Core hypothesis validated | Interesting side results | Core assumption disproven |
| Competition | Still ahead or unique angle | Others approaching differently | Scooped on main contribution |
| Impact | Conclusion-first test passes | Original framing weak, results support different framing | Can't write compelling conclusion even with results |
| Effort remaining | Manageable, clear path | Moderate, toward a different goal | Large, success still uncertain |
| Motivation | Engaged, believes in the work | Curious about pivot direction | Dreading the work |
For Pivot: Must suggest a concrete new framing — not just "consider pivoting." For Kill: Suggest what to salvage (workshop paper, blog post, dataset release, lessons learned).
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.
- 10d ago First seen · 150 lines · 114 tokens per session scan A d288cd70e64b
research-strategist is an agent published in the GitHub repository TobiasBlask/open-paper-machine (18 stars, last pushed 5mo ago), licensed MIT. It adds 114 tokens to every session and 1,389 once invoked, about $0.0006 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.
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…
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
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.