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/.agents/skills/rad-insights/SKILL.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/skills/seanrreid/rad_framework/rad-insights)<a href="https://agentmods.dev/skills/seanrreid/rad_framework/rad-insights"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/seanrreid/rad_framework/rad-insights"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/rad-insights.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 | $0.00045 | $0.18144 |
| Opus 5.5 | $0.00018 | $0.07258 |
| Sonnet 5.5 | $0.00009 | $0.03629 |
| Haiku 4.5 | $0.00005 | $0.01814 |
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.
How it starts
The opening of the file, as written. The whole thing — 1,391 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
the text the user wrote after the skill name (optional):
--since YYYY-MM-DDto limit analysis to cycles on or after that date.--draft-plansto bundle every threshold-crossing Step 3b category into ONE Gate-1-blocked plan viascripts/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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago Changed · +71 lines 6cc6d145ac30
- 13d ago Changed · +96 lines 36c362c19989
- 17d ago Changed · +69 lines 78dad1d75424
- 20d ago First seen · 1,155 lines · 45 tokens per session scan A 2fdd95113610
rad-insights is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 18,144 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 2026-10-10.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…