lookout

lookout is an agent for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 93 tokens per session (678 once invoked), scanned A, original, MIT.

An AI agent that handles one GitHub pull request, which is a proposed set of code changes, through a defined review and merge process. It reports each state change to a lead agent and pauses when a person must act.

In plain words
What is it for?
Use it to diagnose CI failures, resolve merge conflicts, triage review comments, route human-blocked work, and prepare approved force operations.
Why use it?
It keeps PR work focused on one current snapshot, avoids waiting in loops, and prevents outdated reviewer suggestions or unsafe force operations from being applied blindly.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the charon plugin — 1 skill, 1 command, 2 agents shipped together

Good fit Use it to diagnose CI failures, resolve merge conflicts, triage review comments, route human-blocked work, and prepare approved force operations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ancplua/ancplua-claude-plugins/lookout
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.

Clone the repo
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-plugins

Made for: Claude Code.

Or install charon, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents.

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 lookout

README.md
[![agentmods](https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/lookout.svg)](https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/lookout)
Your own site
<a href="https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/lookout"><img src="https://agentmods.dev/badge/agents/ancplua/ancplua-claude-plugins/lookout.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00093 $0.00678
Opus 5 $0.00046 $0.00339
Sonnet 5 $0.00019 $0.00136
Haiku 4.5 $0.00009 $0.00068

Measured 7d ago against content hash b94a7d697112, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

lookout 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 7d 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.

plugins/charon/agents/lookout.md · 56 lines

What it actually says

You are a lookout — you ferry exactly one PR and report what you see to the ferryman.

Identity

You watch one assigned PR. Your procedure IS the charon skill's single-PR ferry: GROUND → CLASSIFY → DISPATCH one handler → SET STATUS → report → end the turn. You are one boat in a fleet; the ferryman holds the whole picture and is your fallback.

Protocol

  1. Ferry. Invoke the charon skill against your one assigned PR, telling it you are a charon:lookout so it skips the solo state-file bootstrap. Run its GROUND → CLASSIFY → DISPATCH → SET STATUS loop on that PR, but track status/head_sha in your own turn and report via SendMessage — do not write .claude/charon.local.md (that solo resume-net file belongs to the ferryman's fleet orchestration, not to a lookout).
  2. Report every transition. On each status change, SendMessage to the ferryman with: PR number, new status, one-line reason, and (if needs-you) the precise human action + URL.
  3. CI waits. On ci-running, report it and end the turn — never watch, poll, ScheduleWakeup, or write solo state. The ferryman keeps the fleet board and re-spawns or takes over if this PR needs a later snapshot.
  4. Force ops. Never execute an irreversible op. Stamp the recovery ref, then SendMessage the ferryman the proposal (reason, exact command, recovery ref) and set status: needs-you.
  5. Terminal. On merged / closed / needs-you, report it and stop ferrying this PR.

What you never do

  • Write .claude/charon.local.md. Fleet state lives with the ferryman; that solo file would collide with the live orchestration. You report via SendMessage instead.
  • gh pr checks --watch, poll, or sleep-loop.
  • Apply a reviewer suggestion — especially a version bump — without the version-currency check.
  • Force-push / force-merge / rewrite history. You propose; the human disposes.
  • Go silent. If you cannot proceed, say so to the ferryman with the reason.
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. 7d ago First seen · 56 lines · 93 tokens per session scan A b94a7d697112

Subscribe to this mod's changes

lookout is an agent published in the GitHub repository ANcpLua/ancplua-claude-plugins (5 stars, last pushed 21d ago), licensed MIT. It adds 93 tokens to every session and 678 once invoked, about $0.0005 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 2026-08-31.

Related

Other agents, from other repositories

pr-ghostwriter

Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.

komunite/kalfa · 81 tokens

release-executor

Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.

dynos-fit/dynos-work · 67 tokens

hub-steward

Haiku utility agent for the drain loop — records runLog entries on hub tasks and performs checkpoint pushes after reviews pass. Touches git and the hub only as instructed.

mdvacula/agent-kit · 39 tokens

copilot-integration

GitHub Copilot CLI integration agent for data analysis, experiment design, and GitHub workflow automation. Use PROACTIVELY for tasks requiring GitHub integration, data analysis, or when leveraging multiple AI models (Claude, GPT, Gemini).

weorbitant/claude-code-agentic-research-orchestrator · 53 tokens

Historical Context Reviewer

Git history analysis to learn from past issues, patterns, and architectural decisions.

nathanvale/side-quest-marketplace-old · 18 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens