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 skills add juicesharp/rpiv-mono --skill design-reviewgit clone --depth 1 https://github.com/juicesharp/rpiv-monoWrote 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/juicesharp/rpiv-mono/design-review)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/design-review"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design-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/juicesharp/rpiv-mono/design-review"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.01746 |
| Opus 5 | $0.00057 | $0.00873 |
| Sonnet 5 | $0.00023 | $0.00349 |
| Haiku 4.5 | $0.00012 | $0.00175 |
Grade A, and why
design-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 12d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review
You run one developer checkpoint over all the per-slice designs a carve slice-design fanout produced. You present the proposed design — across every slice — as a compact summary, and let the developer accept it or adjust a slice. On adjust you apply the change surgically in place to the cited design doc and cascade a changed contract into the slices that depend on it, then re-present. One fan-in pass; the accept↔adjust loop is internal. You do not decompose, re-design from scratch, synthesize, or touch the repo working tree — synthesize merges these designs next, and the plan gate grades the merge.
Input
$ARGUMENTS — flags the carve orchestrator wires from the designs and slices channels. Parse generically:
- Designs — every
--designs <path>flag (repeatable). Each is a per-slice design doc under.rpiv/artifacts/designs/. Its frontmatter carriesslice_n,slice_title, anddepends_on. - Slices — the single
--slices <path>flag: the slice map under.rpiv/artifacts/slices/the designs were cut from (authoritativedeps, Scope, Out of scope).
If you can't identify at least one --designs flag and exactly one --slices flag, print an error and stop — it's a dispatch error.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
The first tab-separated field is <iso> (use as last_updated when you edit a design).
Steps
-
Read every design doc fully (no limit/offset) and read the slice map. From each design note
slice_n,slice_title,depends_on,## Approach,## Key Interfaces,## File Map,## Success Criteria. Build the dependency graph from the designs'depends_on(cross-checked against the slice map'sdeps): for any slice you can reach its transitive dependents (slices that list it, directly or transitively, independs_on). -
Present the consolidated design summary — the whole proposed shape in one view, dependency-ordered. Keep it scannable; the developer reviews the design shape, not every line:
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.
- 12d ago First seen · 79 lines · 115 tokens per session scan A 5deb080bfdc1
design-review is a skill published in the GitHub repository juicesharp/rpiv-mono (780 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 1,746 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…