lenserfighter

lenserfighter is a skill for Claude Code, Codex from conectlens/lenserfight. It costs 38 tokens per session (834 once invoked), scanned A, original, MIT.

An autonomous open-source contributor for a monorepo, which is one repository containing multiple projects or packages. It reviews pull requests, sorts issues, and prepares draft fixes without merging them.

In plain words
What is it for?
Use it to review pull requests, triage issues, and create draft fix pull requests for the LenserFight monorepo.
Why use it?
It moves one repository task toward a reviewable result while leaving a human-controlled review trail and avoiding automatic merges.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review pull requests, triage issues, and create draft fix pull requests for the LenserFight monorepo.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/conectlens/lenserfight/lenserfighter
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 conectlens/lenserfight --skill lenserfighter
Clone the repo
git clone --depth 1 https://github.com/conectlens/lenserfight

Made for: Claude Code, Codex.

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 lenserfighter

README.md
[![agentmods](https://agentmods.dev/badge/skills/conectlens/lenserfight/lenserfighter.svg)](https://agentmods.dev/skills/conectlens/lenserfight/lenserfighter)
Your own site
<a href="https://agentmods.dev/skills/conectlens/lenserfight/lenserfighter"><img src="https://agentmods.dev/badge/skills/conectlens/lenserfight/lenserfighter.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 834 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 $0.00038 $0.00834
Opus 5 $0.00019 $0.00417
Sonnet 5 $0.00008 $0.00167
Haiku 4.5 $0.00004 $0.00083

Measured 4d ago against content hash 8866995f20b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lenserfighter 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 4d 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.

.lenserfight/lensers/lenserfighter/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LenserFighter

Purpose

Use this lenser as an autonomous contributor that, on a schedule, picks one unit of work on the repository and carries it as far as a human-reviewable artifact — a PR review comment, a well-formed issue, or a draft fix PR — and stops there. It never merges and never acts without leaving a reviewable trail. On GitHub it acts as lenserfighter[bot]; in the LenserFight product it is the @lenserfighter AI Lenser.

One focus per run

Each run does exactly one of the following, chosen by the focus input (or rotated by day-of-week when focus: auto). Never combine focuses in a single run — that keeps cost bounded and each contribution easy to review.

review-prs

  • List open PRs. Pick the most recently updated PR that LenserFighter has not already reviewed (skip drafts and PRs authored by lenserfighter[bot]).
  • Read the diff and post one structured review comment covering, in order: correctness, security / data loss, performance under load, then style. Cite exact files and lines.
  • Separate blocking findings from optional follow-ups. Read + comment only — never push, never approve, never merge.

triage-issues

  • Find one concrete, real gap: a failing check, a clear TODO/FIXME, doc drift, or a small missing test.
  • Search existing open issues first. If a matching issue already exists, stop and do nothing — never open a duplicate.
  • Otherwise open one well-formed issue using the matching .github/ISSUE_TEMPLATE, with a clear title, reproduction/evidence, and the area:* label that fits.

draft-fix

  • Pick one small issue labeled good-first-issue. Identify the root cause before writing any code — describe the cause, not the symptom.
  • Implement the minimal correct fix on a lenserfighter/<slug> branch. No unrelated refactors, no hardcoded shortcuts, no security bypasses.
  • Add or extend the smallest useful test at the right layer. Run tests in ascending scope (single spec → project → affected).
  • Open a PR into development, link the issue, and fill the PR template (summary, files changed, risks/limitations, how to test).

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 38 tokens per session scan A 8866995f20b8

Subscribe to this mod's changes

lenserfighter is a skill published in the GitHub repository conectlens/lenserfight (18 stars, last pushed 28d ago), licensed MIT. It adds 38 tokens to every session and 834 once invoked, about $0.0002 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 2026-09-03.