Borrowing it
Nothing to install: this file belongs to seanrreid/RAD_framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/commands/team/rad-research.mdgit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWrote 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/commands/seanrreid/rad_framework/rad-research)<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-research"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-research/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/commands/seanrreid/rad_framework/rad-research"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-research.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 | $0.00047 | $0.02287 |
| Opus 5.5 | $0.00019 | $0.00915 |
| Sonnet 5.5 | $0.00009 | $0.00457 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade B, and why
rad-research scanned grade B with 1 finding 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 21d 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
github | gitlab | bitbucket | forgejo | manual (I'll print instructions instead of running CLI) How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rad-research
Consume a specification artifact and produce a RAD research artifact. This is the R in Research/Architect/Deliver.
Input
$ARGUMENTS should be one of:
- A file path:
docs/prd.md,SPEC.md,issues/42.md - A URL:
https://github.com/org/repo/issues/42 - Empty — you will be prompted to paste the spec inline
Process
Step 1: Load the spec
Determine the input type from $ARGUMENTS:
If $ARGUMENTS starts with http:// or https://:
If your tool can run a sub-agent, delegate the URL fetch with the prompt below;
otherwise fetch it inline with the same caps. Either way, keep only the bounded
SPEC_SUMMARY block in your working context:
Fetch the following URL and extract the key facts needed to design a software
system. Return a bounded summary only — no raw content dump. Max 60 lines.
URL: [URL from $ARGUMENTS]
Extract and return exactly this structure:
SPEC_SUMMARY
title: [project or issue title]
what_is_being_built: [1–3 sentences]
key_requirements:
- [requirement]
- [requirement]
main_domains:
- [domain area — e.g. UI, API, auth, payments, notifications]
constraints:
- [any technical, compliance, or scope constraints mentioned]
acceptance_criteria:
- [if present — otherwise omit this field]
open_questions:
- [anything ambiguous or unresolved in the spec]
END_SPEC_SUMMARY
Parse the SPEC_SUMMARY block. This is your complete spec input — do not
carry the raw page content forward.
If $ARGUMENTS is a file path:
Read the file directly. Extract the same fields from the content. Do not delegate — a single read is sufficient.
If $ARGUMENTS is empty:
Say:
"Paste your PRD, issue description, or spec below. When you're done, say 'done'."
Wait for the user's input. Extract the same fields from what they paste.
Step 2: Confirm the spec read
Present the extracted facts to the user for confirmation:
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.
- 21d ago Changed · +1 lines 921881097829
- 29d ago Changed · +42 lines b0bcbed666dc
- 1mo ago Changed · +20 lines 882e9116d658
- 1mo ago Changed · +19 lines 75afdf3d2362
- 2mo ago First seen · 211 lines · 47 tokens per session scan B e10bf2325d2b
rad-research is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 47 tokens to every session and 2,287 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.