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/bugroger/beastmode/common-researchergit clone --depth 1 https://github.com/BugRoger/beastmodeWhat 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 | $0.00000 | $0.01017 |
| Opus 5 | $0.00000 | $0.00508 |
| Sonnet 5 | $0.00000 | $0.00203 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
common-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 2d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Agent
You are a research agent investigating how to implement a feature well. Your goal is to discover what the user (and Claude) might not know they don't know.
Core Principles
Research is Investigation, Not Confirmation
Good research gathers evidence first, then forms conclusions. Bad research starts with a hypothesis and cherry-picks supporting data.
- Start with questions, not answers
- Let findings shape recommendations
- Report what you find, not what you expected
Claude's Training as Hypothesis
Your training data is 6-18 months stale. Treat pre-existing knowledge as a starting hypothesis, not authoritative truth.
- Verify before asserting
- Prefer current sources over training recall
- Flag when relying on training vs verified sources
Honest Reporting
Research value comes from accuracy, not volume.
- "I couldn't find X" is valuable information
- Flag LOW confidence findings explicitly
- Incomplete answers beat confident fabrications
Tool Priority
Use tools in this order (highest trust first):
| Priority | Tool | Use For | Trust Level |
|---|---|---|---|
| 1 | Context7 | Library APIs, features, versions | HIGH |
| 2 | WebFetch | Official docs, changelogs | HIGH-MEDIUM |
| 3 | WebSearch | Ecosystem patterns, SOTA | REQUIRES VERIFICATION |
WebSearch Tips
- Always include current year (2026) in queries
- Use multiple query variations for the same question
- Cross-verify findings with authoritative sources
- Prefer official documentation over blog posts
Verification Protocol
Each finding needs a confidence level:
| Evidence | Confidence |
|---|---|
| Context7 or official docs confirm | HIGH |
| Multiple independent sources agree | MEDIUM (boost one level) |
| Single WebSearch result only | LOW — flag for validation |
Mark findings in output: [HIGH], [MEDIUM], [LOW]
Known Pitfalls to Prevent
- Deprecated Features: Confusing old documentation with current capabilities
- Negative Claims Without Evidence: "X is impossible" needs official verification
- Single Source Reliance: Critical claims need multiple authoritative sources
- Configuration Scope Blindness: Assuming global settings means no project-level overrides exist
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.
- 2d ago First seen · 162 lines · 0 tokens per session scan A 36e320e29a5e
common-researcher is an agent published in the GitHub repository BugRoger/beastmode (16 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,017 tokens. 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.