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/roomi-fields/paper-trail/researchergit clone --depth 1 https://github.com/roomi-fields/paper-trailWrote 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/roomi-fields/paper-trail/researcher)<a href="https://agentmods.dev/agents/roomi-fields/paper-trail/researcher"><img src="https://agentmods.dev/badge/agents/roomi-fields/paper-trail/researcher.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 | $0.00058 | $0.01315 |
| Opus 5 | $0.00029 | $0.00658 |
| Sonnet 5 | $0.00012 | $0.00263 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
researcher 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 6d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-agent : researcher
Role
Perform exhaustive multi-source academic search for a given topic.
Returns a structured list of candidate references that sota-writer
phase A will then push into the registry as candidate state for
acquisition.
Input contract
topic: "Petri nets in music notation" # required
domain: "computer-science" # optional (filters fieldsOfStudy)
year_range: [2010, 2026] # optional
max_candidates: 50 # optional, default 50
extra_keywords: ["formal grammar", "MIDI"] # optional
include_notebooklm: false # optional, default false
include_websearch: false # optional, default false
What this agent does
Step 1 — Multi-source paper search (mandatory)
Invokes paper-search MCP across multiple platforms :
| Question type | Priority tool |
|---|---|
| General academic papers | mcp__paper-search__search_papers (unified) |
| Recent preprints (CS, AI, math, physics) | mcp__paper-search__search_arxiv |
| Cross-domain aggregator | mcp__paper-search__search_openalex |
| Formal linguistics, NLP | mcp__paper-search__search_semantic |
| Medical / biomedical | mcp__paper-search__search_pubmed |
| French academic | mcp__paper-search__search_hal |
| DOI lookup | mcp__paper-search__get_crossref_paper_by_doi |
Filters applied :
- Relevance (abstract keyword match)
- Year range
- Citation count (preference for cited papers but don't exclude recent low-citation papers)
Step 2 — Local corpus search (if configured)
If mcp__rtfm__* MCP is configured for the project, query the local
indexed corpus for additional matches not surfaced by remote APIs.
Step 3 — Books corpus (optional)
If include_notebooklm: true and mcp__notebooklm__* MCP is configured,
query the books corpus via notebook_ask for chapters/sections relevant
to the topic.
Step 4 — Web search complement (optional)
If include_websearch: true, complement with WebSearch for :
- Course pages
- Personal/lab pages
- archive.org records
- Conference proceedings not in S2/OpenAlex
- Pre-publication tech reports
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.
- 6d ago First seen · 153 lines · 58 tokens per session scan A 88ce4d58c8dc
researcher is an agent published in the GitHub repository roomi-fields/paper-trail (5 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,315 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 2026-08-31.
Other agents, from other repositories
reviewer
The Reviewer of the aSPARK team. Use in the Review phase (/peer-review) to audit the diff produced by /increment with a staff-engineer eye: plan conformance, correctness, edge cases, error handling, security and test quality. Writes the review report and may fix obvious low-risk issues directly.
designer
The Designer of the aSPARK team. Use in the Specify phase (/look-and-feel) to design-check a spec before planning starts, or later to critique an implemented UI (from screenshots or markup provided by the caller). Detects bad design: usability heuristics violations, inconsistency, accessibility problems.
seo-manager
SEO specialist. Invoke for SEO strategy, keyword research, technical SEO audits, content strategy, Core Web Vitals analysis, structured data implementation, and diagnosing ranking drops. All three SEO pillars: technical, content, and authority.
product-manager
Product management specialist. Invoke for product discovery, user story writing, acceptance criteria, PRDs, prioritisation frameworks, roadmaps, success metrics, and opportunity assessment. Distinct from project-manager, use this for what to build, not how to deliver it.
project-manager
Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.
kotlin-code-reviewer
Kotlin/Java code review specialist. Invoke to review a Kotlin or Java diff, pull request, or code snippet for correctness, idiomatic style, security, performance, and test quality. Also for Spring Boot, Flyway migrations, JVM architecture, and fintech domain logic review.