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.
git clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote 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.
[](https://agentmods.dev/agents/ancplua/ancplua-claude-plugins/lookout)<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>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.
| Model | Per session | Once 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 |
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.
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
- Ferry. Invoke the
charonskill against your one assigned PR, telling it you are acharon:lookoutso it skips the solo state-file bootstrap. Run its GROUND → CLASSIFY → DISPATCH → SET STATUS loop on that PR, but trackstatus/head_shain 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). - 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. - 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. - 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. - 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.
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.
- 7d ago First seen · 56 lines · 93 tokens per session scan A b94a7d697112
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.
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.
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.
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.
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).
Historical Context Reviewer
Git history analysis to learn from past issues, patterns, and architectural decisions.
Demonstrate
Agent for demonstrating VS Code features.