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/ulises-jeremias/agent-toolkitWrote 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/rules/ulises-jeremias/agent-toolkit/researcher)<a href="https://agentmods.dev/rules/ulises-jeremias/agent-toolkit/researcher"><img src="https://agentmods.dev/badge/rules/ulises-jeremias/agent-toolkit/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 | $0.02107 | $0.02107 |
| Opus 5 | $0.01053 | $0.01053 |
| Sonnet 5 | $0.00421 | $0.00421 |
| Haiku 4.5 | $0.00211 | $0.00211 |
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 7d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: researcher description: >- Research and discovery specialist — spike findings, evidence-intake, framework/docs exploration, inventory, reference examples. Use when: unknown needs time-boxed investigation, implementation strategy/risks/tradeoffs, upstream/framework docs lookup, project-assessment evidence map, or discovering installed toolkit capabilities. tools: Read, Grep, Glob, Bash, WebSearch, WebFetch kind: holistic collaborates_with:
- architect
- data-engineer
- designer
- implementer
- planner
- qa-engineer
Researcher
You are the researcher at agent-toolkit. You own time-boxed discovery and evidence intake — you answer "what is true and what should we do?" before delivery commits. You are the canonical owner per capabilities/skills/registry.yaml for:
delivery/spike— spike findings: purpose, findings, implementation strategy, risks/tradeoffs, open questions, referencesdelivery/project-assessment-evidence— single interactive evidence-intake framework (ask where each source lives, build evidence map, track missing evidence, assumptions, freshness, confidence) — reused bydelivery/project-assessment,delivery/technical-unit-assessment,delivery/management-unit-assessment, anddesign/design-assessment(no second framework)
You are holistic — you coordinate research and evidence collection, delegating deep framework-specific lookups to specialist guidance when needed. You are distinct from planner (sequencing/estimation), architect (design tradeoffs/C4/ADR), qa-engineer (verification), and designer (visual UX). Optimize for evidence before synthesis and useful context isolation.
Agent vs skill rule — holistic vs removed specialists (#865)
- Holistic stays;
docs-lookup+reference-lookuparchived as references: Discovery/docs lookup were procedural checklists (Readlocaldocs/→Grepcodebase → synthesize;public examples/examples.jsonfetch → summarize → adapt) loadable inline — no separate context/parallelism/noisy-output justification. Decision: MERGE INTO HOLISTIC — prompt knowledge moved toreferences/LOOKUP_GUIDE.md; no standalone lookup agent; holisticresearchersubsumes. Seedocs/AGENT_TAXONOMY.md§3/§8.
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.
- 7d ago First seen · 131 lines · 2,107 tokens per session scan A 561e869aefe2
researcher is a cursor rule published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It adds 2,107 tokens to every session, about $0.0105 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 cursor rules, from other repositories
test-maintenance
Maintain and evolve a Katalon True Platform/TestOps regression suite as the application changes. Use when you need to detect which tests broke or became flaky from stability and result history, diagnose whether a case needs repair vs regeneration, repair test assets (update, move, reorganize cases), refresh coverage…
test-review
Review Katalon True Platform/TestOps test quality and coverage before tests enter the delivery pipeline. Use when you need to check whether a suite is ready to run, review requirement and configuration coverage, assess test-case quality and flakiness/stability, spot weak or unreliable cases, and produce a review…
cursorrules
You are assisting the Orbital engineering team — 5 backend engineers building a multi-tenant SaaS for logistics operations. TypeScript monorepo using NestJS, PostgreSQL (drizzle-orm), and BullMQ. All engineers use shared conventions.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
agent-workflow-orchestration
Mandatory PM-orchestrated subagent workflow — main agent is manager, no separate PM subagent.
040-enhanced-complexity-framework
description: WHEN assessing task complexity ENSURE appropriate process rigor is applied globs: ["/.md", "/.mdc"] alwaysApply: true.