lens-grade

lens-grade is a skill for Claude Code from juicesharp/rpiv-mono. It costs 70 tokens per session (760 once invoked), scanned A, original, MIT.

A narrow grading step that judges one file or working-tree change against one pass-or-fail question and writes a JSON result. It reads the relevant evidence but does not edit files or run the code.

In plain words
What is it for?
Use it in a review workflow to check one rubric, record whether it passes, and report evidence and severity for failures.
Why use it?
It keeps reviews focused and makes each finding traceable to code that was actually inspected. Separate grading steps can assess different concerns without mixing their standards.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it in a review workflow to check one rubric, record whether it passes, and report evidence and severity for failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juicesharp/rpiv-mono/lens-grade
Install

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.

Any agent
npx skills add juicesharp/rpiv-mono --skill lens-grade
Clone the repo
git clone --depth 1 https://github.com/juicesharp/rpiv-mono

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 lens-grade

README.md
[![agentmods](https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/lens-grade/github.svg)](https://agentmods.dev/skills/juicesharp/rpiv-mono/lens-grade)
Your own site
<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/lens-grade"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/lens-grade/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 lens-grade

Your own site · 80×15
<a href="https://agentmods.dev/skills/juicesharp/rpiv-mono/lens-grade"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-mono/lens-grade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 760 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 $0.00070 $0.00760
Opus 5.5 $0.00028 $0.00304
Sonnet 5.5 $0.00014 $0.00152
Haiku 4.5 $0.00007 $0.00076

Measured 6d ago against content hash 29e6528a3a18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lens-grade 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 6d 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.

packages/rpiv-pi/skills/lens-grade/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lens grade

You are one skeptic on a panel. You judge one target through one lens and write one JSON verdict. Other lenses run in parallel in their own sessions; stay inside yours.

Input

$ARGUMENTS carries:

  • --unit, --lens, --round, --generation: identity. Copy them verbatim into the verdict.
  • --target: the artifact path to judge. If the target says "working tree", judge git diff HEAD plus untracked files (git status --porcelain).
  • --<name> <path> (for example --goal, --research, --acceptance, --plans): read-only context. Read each one fully.
  • --out: the directory for the verdict.
  • --rubric: the pass/fail question for this lens. It is the ONLY standard you apply.

Procedure

  1. Read the context files, then the target. Batch your reads: issue several Read/Grep calls per turn, never one at a time.
  2. For every claim the rubric makes you check, open the code it touches before ruling. A finding needs observed evidence: a file:line you read.
  3. Rule by your 6th tool turn.
    • pass: true when the rubric's FAIL conditions do not hold.
    • pass: false otherwise, with severity:
      • high: the target is broken as written.
      • medium: a real defect the rubric names.
      • low: a nit or a style issue. low never blocks.
  4. Write the verdict with the Write tool; end your reply with <lens>: PASS or <lens>: FAIL (<severity>) — not the path, which the panel reads from disk.

Verdict

Write <out>/<unit>__<lens>__r<round>g<generation>.json — the four identity flags verbatim, no timestamp.

{
  "unit": "plan",
  "lens": "correctness",
  "round": 2,
  "generation": 0,
  "pass": false,
  "severity": "medium",
  "findings": [
    { "detail": "Phase 2 calls FooStore.save(_:) — the method is save(item:)", "where": "Sources/Foo/FooStore.swift:41" }
  ],
  "feedback": "One or two sentences telling the corrector exactly what to change. Scope it to the findings."
}

Rules:

  • Keep each detail stable and specific. The loop compares findings across rounds, and a finding that survives a correction unchanged stops the loop.
  • No finding without a where.
  • Do not grade outside your lens, and do not rewrite the target.

Read the full file on GitHub · 63 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. 6d ago Changed 29e6528a3a18
  2. 17d ago First seen · 63 lines · 70 tokens per session scan A 1e8dccc38b88

Subscribe to this mod's changes

lens-grade is a skill published in the GitHub repository juicesharp/rpiv-mono (901 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 760 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 2026-10-01.

Related

Other skills, from other repositories

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

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"…

umputun/revdiff · 84 tokens

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…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

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…

dzhng/skills · 162 tokens

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…

LilMGenius/paperthin · 70 tokens