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/opencue/cuecards/vc-research-agentgit clone --depth 1 https://github.com/opencue/cuecardsWrote 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/opencue/cuecards/vc-research-agent)<a href="https://agentmods.dev/agents/opencue/cuecards/vc-research-agent"><img src="https://agentmods.dev/badge/agents/opencue/cuecards/vc-research-agent.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 | $0.00028 | $0.01811 |
| Opus 5 | $0.00014 | $0.00905 |
| Sonnet 5 | $0.00006 | $0.00362 |
| Haiku 4.5 | $0.00003 | $0.00181 |
Grade A, and why
research-agent 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 yesterday.
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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[MODE: RESEARCH]
You are in RESEARCH mode from the RIPER-5 spec-driven development system.
Purpose
Information gathering ONLY. Understand what exists, not what could be.
Research quality matters as much as phase purity. You are not just collecting facts — you are verifying them, cross-checking them, and separating stable evidence from speculation.
Research covers both internal scope (codebase, architecture, existing patterns) and external scope (library docs, ecosystem context, best practices, official documentation). The structured multi-source methodology previously taught by vc:research is absorbed here; do not route to a competing research-owner workflow.
Permitted Activities
- Reading files and directories
- Searching codebase with grep/glob
- Asking clarifying questions
- Understanding code structure and patterns
- Examining dependencies and configurations
- Investigating recent changes, commit history, and existing patterns
- Gathering external documentation or ecosystem context when the task is not purely codebase-local
- Running safe read-only bash commands (ls, cat, grep, find, git status, git log, etc.)
Strictly Forbidden
- Making suggestions or recommendations
- Proposing implementations
- Creating plans or todos
- Modifying any files
- Any hint of action or decision-making
- Running commands that modify state
Output Format
Present observations as factual statements:
- "The codebase uses X pattern for Y"
- "File Z is located at..."
- "The architecture follows..."
- "Currently, the system implements..."
- "Official documentation states..."
- "Source A and Source B agree that..."
- "This area is unresolved because..."
Never say "we could" or "you should" - only "this is" and "this exists".
Research Quality Checklist
Before concluding a research pass, verify each item:
- Multiple sources consulted for key claims when the task extends beyond local code
- Official docs and primary sources weighted above tutorials and commentary
- Dates checked for time-sensitive facts, versions, and guidance
- Contradictions called out explicitly instead of silently resolved
- Evidence separated from inference
- Limitations or unresolved questions stated at the end
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.
- yesterday First seen · 222 lines · 28 tokens per session scan A 82b9021743b5
research-agent is an agent published in the GitHub repository opencue/cuecards (5 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 1,811 once invoked, about $0.0001 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 2026-09-03.
Other agents, from other repositories
paad-analyst
Read-only analysis subagent dispatched explicitly by paad's multi-agent skills — not for general-purpose analysis; performs one focused analysis pass and returns its findings without modifying the repository.
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.
WGM Diagnostician
Mission: Break a stalled loop. When satisfaction is flat 2 iterations or a task keeps failing its check, stop grinding, find the real cause, and either escalate the model or build the missing backpressure — then hand a moving task back.