RAD_framework: Command for Claude Code

.claude/commands/shared/rad-insights.md

rad-insights is a command for Claude Code from seanrreid/RAD_framework. It costs 41 tokens per session (18,133 once invoked), scanned A, original, MIT.

A command that studies records from RAD code-review cycles stored in `.agents/findings.jsonl`. It groups repeated issues, problem-heavy files, and changes in review results over time.

In plain words
What is it for?
Use it to count finding categories, identify files that often need attention, and compare review history from a chosen date onward.
Why use it?
It helps a team see recurring review problems instead of reading each review separately. With little history, it reports the available findings without pretending there is a reliable pattern.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

This is seanrreid/RAD_framework's own configuration. It tells Claude Code how to work on RAD_framework itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RAD_framework configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is DEFAULT_BRANCH=$(node harness/cli.js config get default_branch) || { echo "rework/load: cannot resolve default_branch" >&2; exit 1; }.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/seanrreid/RAD_framework/main/.claude/commands/shared/rad-insights.md
Clone the repo
git clone --depth 1 https://github.com/seanrreid/RAD_framework

Made for: Claude Code.

Wrote 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.

agentmods badge for rad-insights

README.md
[![agentmods](https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-insights/github.svg)](https://agentmods.dev/commands/seanrreid/rad_framework/rad-insights)
Your own site
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-insights"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-insights/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.

agentmods 80×15 button for rad-insights

Your own site · 80×15
<a href="https://agentmods.dev/commands/seanrreid/rad_framework/rad-insights"><img src="https://agentmods.dev/badge/commands/seanrreid/rad_framework/rad-insights.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 18,133 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.18133
Opus 5.5 $0.00016 $0.07253
Sonnet 5.5 $0.00008 $0.03627
Haiku 4.5 $0.00004 $0.01813

Measured 3d ago against content hash 0c4237745164, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rad-insights 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 3d 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.

.claude/commands/shared/rad-insights.md · 1,390 lines

How it starts

The opening of the file, as written. The whole thing — 1,390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/rad-insights

Analyze finding patterns across all recorded RAD review cycles.

Input

$ARGUMENTS (optional):

  • --since YYYY-MM-DD to limit analysis to cycles on or after that date.
  • --draft-plans to bundle every threshold-crossing Step 3b category into ONE Gate-1-blocked plan via scripts/draft-insights-plan.sh (see Step 3b). Without this flag the skill drafts nothing and Step 3b output is unchanged.

Process

Step 1: Check for findings log

if [ ! -f .agents/findings.jsonl ]; then
  echo "No findings log found. Run /rad-review on at least one rad/ work branch first."
  exit 0
fi

Count records to determine report depth:

# Total cycles
jq -r 'select(.type=="cycle")' .agents/findings.jsonl | jq -s 'length'

# Total findings
jq -r 'select(.type=="finding")' .agents/findings.jsonl | jq -s 'length'

If fewer than 3 cycles exist, note the limited data and output a raw findings list instead of a pattern report.

Step 2: Apply date filter (if --since provided)

# Filter findings to on/after the provided date
jq -r --arg since "[DATE]" 'select(.date >= $since)' .agents/findings.jsonl

Step 3: Compute finding frequencies

# Category frequency (all priorities)
jq -r 'select(.type=="finding") | .category' .agents/findings.jsonl \
  | sort | uniq -c | sort -rn

# HIGH findings by category
jq -r 'select(.type=="finding" and .priority=="HIGH") | .category' .agents/findings.jsonl \
  | sort | uniq -c | sort -rn

# Finding frequency per file (top 10)
jq -r 'select(.type=="finding") | .file' .agents/findings.jsonl \
  | sort | uniq -c | sort -rn | head -10

# Findings by reviewer
jq -r 'select(.type=="finding") | .reviewer' .agents/findings.jsonl \
  | sort | uniq -c | sort -rn

Step 3b: Findings Recurrence — convention/lint suggestions

A category that keeps recurring across review cycles is a signal the project is missing a convention (or a lint rule) that would prevent it. This step turns the Step 3 category counts into suggestions only — every output is framed "suggestion — apply via PR; never auto-applied". This skill NEVER edits AGENTS.md, CLAUDE.md or scripts/lint-plan.sh itself.

Read the full file on GitHub · 1,390 lines

Changes

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.

  1. 3d ago Changed · +71 lines 0c4237745164
  2. 13d ago Changed · +96 lines 315ff69e2af4
  3. 17d ago Changed · +69 lines 83d741c0bf37
  4. 20d ago Changed · -2 lines 651cc55eb999
  5. 23d ago Changed c765855da1bf
  6. 1mo ago Changed · +124 lines edb2d9b6fb2e
  7. 1mo ago Changed · +108 lines 30caffdda79d
  8. 1mo ago Changed · +515 lines 804459dc0542
  9. 2mo ago First seen · 409 lines · 41 tokens per session scan A 469c8af21330

Subscribe to this mod's changes

rad-insights is a command published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 18,133 once invoked, about $0.0002 per session on Opus 5.5. 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.