run-lenserfighter

run-lenserfighter is an agent for Claude Code from conectlens/lenserfight. It costs 38 tokens per session (1,475 once invoked), scanned A, original, MIT.

An autonomous AI agent that runs on a schedule to review pull requests, triage issues, or draft small fixes for a GitHub repository without merging them.

In plain words
What is it for?
It is for scheduled pull-request reviews, issue triage, and draft fix pull requests through GitHub Actions.
Why use it?
It handles routine repository work while keeping changes subject to normal CI checks and human review.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Claude Code.

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.

agentmods
npx agentmods add agents/conectlens/lenserfight/run-lenserfighter
Clone the repo
git clone --depth 1 https://github.com/conectlens/lenserfight

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 run-lenserfighter

README.md
[![agentmods](https://agentmods.dev/badge/agents/conectlens/lenserfight/run-lenserfighter.svg)](https://agentmods.dev/agents/conectlens/lenserfight/run-lenserfighter)
Your own site
<a href="https://agentmods.dev/agents/conectlens/lenserfight/run-lenserfighter"><img src="https://agentmods.dev/badge/agents/conectlens/lenserfight/run-lenserfighter.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,475 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.01475
Opus 5 $0.00019 $0.00737
Sonnet 5 $0.00008 $0.00295
Haiku 4.5 $0.00004 $0.00147

Measured 2d ago against content hash ea3ebcfecfe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

run-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 2d 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.

docs/en/how-to/agents/run-lenserfighter.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the LenserFighter Autonomous Contributor

LenserFighter is an autonomous AI Lenser that contributes to a GitHub repository on a schedule. Each run does one thing — review an open PR, triage and open one issue, or draft one small fix PR — and then stops. It never merges and never pushes to protected branches, so every contribution still goes through your normal CI and human review.

  • On GitHub it acts as the lenserfighter[bot] GitHub App.
  • In the LenserFight product it is the @lenserfighter AI Lenser.

The runtime is a GitHub Actions workflow (.github/workflows/lenserfighter.yml) that runs anthropics/claude-code-action — the same way Claude contributes to GitHub repositories. Its behavior is defined entirely by the persona file .lenserfight/lensers/lenserfighter/SKILL.md.

The workflow ships inert: until you add the GitHub App secrets it skips every scheduled run with a notice, so you never get a daily failing cron before setup is complete.


What it does each run

Focus Action Writes?
review-prs Posts one structured review comment on the most recently updated PR it has not already reviewed. Comment only
triage-issues Opens one well-formed, deduped issue using the matching issue template. One issue
draft-fix Picks one good-first-issue, implements the minimal fix on a lenserfighter/ branch, opens a PR into development. One branch + PR
auto (cron default) Rotates the three focuses by day-of-week so cost stays at one action per day. Varies

Read the full file on GitHub · 121 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. 2d ago First seen · 121 lines · 38 tokens per session scan A ea3ebcfecfe8

Subscribe to this mod's changes

run-lenserfighter is an agent published in the GitHub repository conectlens/lenserfight (19 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 1,475 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.

Related

Other agents, from other repositories