agentmods.dev

pi-lens: Agent for Claude Code

.claude/agents/pi-lens-reviewer.md

pi-lens-reviewer is an agent for Claude Code from apmantza/pi-lens. It costs 70 tokens per session (490 once invoked), scanned A, original, MIT.

A pre-merge review procedure for pi-lens, a VS Code extension that helps coding agents work. It checks a proposed code change, called a pull request, by trying to find and prove defects before it is merged.

In plain words
What is it for?
Use it to review pi-lens pull requests, check merge status, verify that claimed failing tests really fail before the fix, and run targeted checks for defects. It reports findings internally without merging or commenting on GitHub.
Why use it?
It reduces the risk of merging a change that appears correct but has conflicts, ineffective tests, or overlooked bugs. It also keeps review standards consistent for every pull request.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents; mentions Claude Code.

This is apmantza/pi-lens's own configuration. It tells Claude Code how to work on pi-lens itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pi-lens configures →

not rated 514repo +7 changed 6d ago A scan 70 tokens original MIT
View source ↗ apmantza/pi-lens npmjs.com
Reuse

Borrowing it

Nothing to install: this file belongs to apmantza/pi-lens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/apmantza/pi-lens/master/.claude/agents/pi-lens-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/apmantza/pi-lens

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 pi-lens-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/apmantza/pi-lens/pi-lens-reviewer/github.svg)](https://agentmods.dev/agents/apmantza/pi-lens/pi-lens-reviewer)
Your own site
<a href="https://agentmods.dev/agents/apmantza/pi-lens/pi-lens-reviewer"><img src="https://agentmods.dev/badge/agents/apmantza/pi-lens/pi-lens-reviewer/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 pi-lens-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/apmantza/pi-lens/pi-lens-reviewer"><img src="https://agentmods.dev/badge/agents/apmantza/pi-lens/pi-lens-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 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 $0.00490
Opus 5.5 $0.00028 $0.00196
Sonnet 5.5 $0.00014 $0.00098
Haiku 4.5 $0.00007 $0.00049

Measured 6d ago against content hash c4ad56af6ca1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-lens-reviewer 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.

.claude/agents/pi-lens-reviewer.md · 33 lines

What it actually says

You are the pi-lens adversarial reviewer. Before any other step, read docs/pi-lens-subagent.md and docs/pi-lens-reviewer.md in full, then follow them. They own every role rule, after the engineering principles (already in your global instructions) and AGENTS.md. This file adds only what is specific to the Claude Code harness.

  • You are a leaf: never spawn agents (the disallowedTools grant enforces it, #2607).
  • Review in your own worktree: the one the brief names, or node scripts/pr-worktree.mjs open <PR> [--merge], closed with node scripts/pr-worktree.mjs close <path> when the report is written. The shared main checkout is not yours: never switch its branch or rebuild it; a report that leaves it off master is a finding against the report (#2704).
  • Your session scratchpad is shared with every lane of the session and sits on /tmp; write nothing there, not even probes (#3526, #3850).
  • You report to the orchestrator only; REVIEW.md plus your hand-back is the whole output.
  • Deliver the final report through SubagentHandback when the harness offers it; trailing text does not reach the orchestrator.
  • When the brief names a hand-back file, the harness default against report .md files does not cover it, nor REVIEW.md. Write those files first, then call SubagentHandback with the summary and the hand-back path.
  • The handback-cap hook refuses a SubagentHandback call over 30 non-blank lines; the per-lane caps live in docs/pi-lens-subagent.md "Deliverable".
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 · +2 lines c4ad56af6ca1
  2. 10d ago Changed · +3 lines 9a4c20c73f62
  3. 1mo ago Changed · -333 lines · +4 tokens per session 8e496ea440da
  4. 1mo ago Changed · +18 lines 9730b1cffda3
  5. 1mo ago Changed · +3 lines bb4e8a57e636
  6. 1mo ago Changed · +17 lines 4e54a3db0cf1
  7. 1mo ago Changed · +18 lines 1542f97380ad
  8. 1mo ago Changed · +2 lines 029a40e980eb
  9. 1mo ago Changed · +26 lines 809f1dc06f5c
  10. 1mo ago First seen · 277 lines · 66 tokens per session scan A daff80c9af79

Subscribe to this mod's changes

pi-lens-reviewer is an agent published in the GitHub repository apmantza/pi-lens (514 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 490 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 2026-08-30.

Code review
Related

pi-lens-reviewer compared with agents from other repositories

pi-lens-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pi-lens-reviewerapmantza/pi-lensAgent514yesterdayMITA70Claude Code
cpp-revieweraffaan-m/ECCAgent298k4d agoMITA41Claude Code, Kiro
thermo-nuclear-code-quality-review-subagentmichael-denyer/pstack-claudeAgent4.1kyesterdayMITA68Claude Code
review-obsidian-guidelinesuphy/obsidian-reminderAgent662yesterdayMITA63Claude Code
karimo-implementeropensesh/KARIMOAgent29024d agoApache-2.0A49Claude Code
atomic-auditordamusix/atomic-claudeAgent1154d agoMITA169Claude Code
reviewergenkovich/sddAgent19922d agoMITA81Claude Code