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-review/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-review)<a href="https://agentmods.dev/skills/seanrreid/rad_framework/rad-review"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/rad-review/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-review"><img src="https://agentmods.dev/badge/skills/seanrreid/rad_framework/rad-review.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 | $0.00064 | $0.01125 |
| Opus 5.5 | $0.00026 | $0.00450 |
| Sonnet 5.5 | $0.00013 | $0.00225 |
| Haiku 4.5 | $0.00006 | $0.00112 |
Grade A, and why
rad-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rad-review
Review the current rad/<feature> work branch before requesting architect
review. This review is strictly read-only.
Input
Read the text the user wrote after the skill name (optional): specific files to review. If empty, review every file changed on the branch since it diverged from the default branch.
Process
Step 1: Resolve the branch, plan, and base
BASE=$(scripts/get-default-branch.sh)
BRANCH=$(git branch --show-current)
FEATURE=${BRANCH#rad/}
PLAN=".agents/plans/$FEATURE.md"
git diff "$BASE"...HEAD --name-only
- If
scripts/get-default-branch.shexits non-zero, report its stderr and stop. - If the branch name does not start with
rad/, or$PLANdoes not exist, report that and stop: this review needs a RAD work branch and its plan.
Step 2: Deterministic checks
Run each command and include its full output and exit code in the report:
scripts/check-scope.sh "$PLAN" "$BRANCH" "$BASE"
scripts/lint-plan.sh "$PLAN"
scripts/check-approval-blockers.sh "$PLAN"
scripts/check-tests-present.sh "$PLAN"
check-scope.sh: any out-of-scope file is HIGH priority.lint-plan.sh: advisory only; it does not change the review outcome.check-approval-blockers.sh: exit 1 lists blockers on stderr; note that they will block approval. Exit 2 is an error; report it.check-tests-present.sh: report any task missing its tests.
A non-zero exit from any of these is reported, never a reason to stop the review.
Step 3: Reviewer sub-agents
- Spawn the
quality-reviewersub-agent, defined at.codex/agents/quality-reviewer.toml, on the changed files (or the files the user named). Include its full findings report. - UI files are changed files ending in
.html,.css,.scss,.jsx,.tsx,.vueor.svelte. When any UI file changed, also spawn theaccessibility-reviewersub-agent, defined at.codex/agents/accessibility-reviewer.toml, on those files and include its full findings report. Otherwise note that no UI files changed. - When any UI file changed, also spawn the
ui-integrity-reviewersub-agent, defined at.codex/agents/ui-integrity-reviewer.toml, on those files and include its full findings report and sibling-sweep table. Otherwise printUI integrity: skipped (no frontend files changed)and continue. It is advisory: its findings are listed but never counted as blocking, and never approve a plan or change severity routing.
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.
- 8d ago Changed · +6 lines · +4 tokens per session cba9aec2a8c5
- 20d ago Changed · +24 lines a63e6d9fb35b
- 23d ago First seen · 80 lines · 60 tokens per session scan A 51eb4f33e387
rad-review is a skill published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,125 once invoked, about $0.0003 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 2026-10-06.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.