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 architecture-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/architecture-review)<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/architecture-review"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/architecture-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/architecture-review"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/architecture-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 | $0.00126 | $0.05823 |
| Opus 5.5 | $0.00050 | $0.02329 |
| Sonnet 5.5 | $0.00025 | $0.01165 |
| Haiku 4.5 | $0.00013 | $0.00582 |
Grade A, and why
architecture-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 2mo 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 — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review
You are tasked with conducting a layer-by-layer architecture review of a target module, producing a single living artifact that captures every triaged finding plus a phased polish plan downstream skills can consume.
Input
$ARGUMENTS — target path (file, directory, or module). Empty input triggers a developer checkpoint to identify the target.
Metadata
node "${SKILL_DIR}/../_shared/now.mjs"
echo
node "${SKILL_DIR}/../_shared/git-context.mjs"
Copy values verbatim — do not reformat the timezone offset.
Flow
- Identify target → 2. Plan layer structure → 3. Layer-split checkpoint → 4. Skeleton artifact → 5. Per-layer review (loop) → 6. Capture emergent principles → 7. Synthesize cross-cutting themes → 8. Phased polish plan → 9. Present and chain → 10. Follow-ups
The final artifact is blueprint-consumable per phase.
Steps
Step 1: Identify the Target
-
Argument is empty: use the
ask_user_questiontool with the following question: "What are we reviewing?". Header: "Target". Options: "Single module" (one package / project / crate / namespace directory); "Single subdirectory" (a subtree inside a module); "Single file" (deep review of one large file). The automaticType something.row accepts a custom target.Headeris capped at ≤16 characters (MAX_HEADER_LENGTH = 16— longer values are rejected).
-
Validate the target exists. Use
lsvia the Bash tool on the resolved path. If missing, ask for a corrected path. -
Capture target context into main context:
- Read the target's manifest file if one exists (
package.json,pom.xml,*.csproj,Cargo.toml,pyproject.toml,go.mod,build.gradle[.kts],mix.exs). The manifest names public exports, dependencies, and ecosystem. - Read any
README.mdor architecture doc at the target root. - For a single file: read it FULLY (no limit/offset).
- Enumerate all source files in scope via
ls -Rorfind, filtering by the extensions visible at the target root. Record total file count and LOC ballpark.
- Read the target's manifest file if one exists (
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.
- 2mo ago First seen · 351 lines · 126 tokens per session scan A c9a4e74b4eb6
architecture-review is a skill published in the GitHub repository juicesharp/rpiv-mono (934 stars, last pushed 6d ago), licensed MIT. It adds 126 tokens to every session and 5,823 once invoked, about $0.0005 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 2026-08-30.
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…