charon

charon is a skill for Claude Code from ANcpLua/ancplua-claude-plugins. It costs 134 tokens per session (3,341 once invoked), scanned B, original, MIT.

A skill for moving one GitHub pull request toward merge in short, state-based steps. It reads the live PR state, performs one appropriate action, records the result, and ends the turn.

In plain words
What is it for?
Use it to fix CI at its root cause, repair conflicts, check whether review comments match current code, handle human decisions, and pause before force operations.
Why use it?
It prevents stale decisions, tight polling loops, blind reviewer changes, and unsafe force operations while work is still being checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

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

Good fit Use it to fix CI at its root cause, repair conflicts, check whether review comments match current code, handle human decisions, and pause before force operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ancplua/ancplua-claude-plugins/charon
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 ANcpLua/ancplua-claude-plugins --skill charon
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 charon

README.md
[![agentmods](https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/charon/github.svg)](https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/charon)
Your own site
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/charon"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/charon/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 charon

Your own site · 80×15
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/charon"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/charon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,341 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00134 $0.03341
Opus 5 $0.00067 $0.01670
Sonnet 5 $0.00027 $0.00668
Haiku 4.5 $0.00013 $0.00334

Measured 9d ago against content hash e0d8e9739aa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

charon scanned grade B with 1 finding 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 9d 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.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

(2) Never tell the user to "just wait" — either you are doing something, or you name the
plugins/charon/skills/charon/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Charon — the PR ferry

You carry one PR across the river to merge. Each turn is one iteration:

GROUND → CLASSIFY → DISPATCH (one handler) → SET STATUS → END TURN

You do not loop by hand. The Stop hook re-enters you while work is actionable, lets you rest while CI runs, and finishes when the PR is merged / closed / needs-you. Your only jobs each iteration: gather truth, do one honest unit of work, and record an honest status.

Three laws. (1) Never gh pr checks --watch; never poll or sleep in a tight loop. (2) Never tell the user to "just wait" — either you are doing something, or you name the one thing only they can do. (3) Never apply a reviewer suggestion blindly — verify it against the real code, and verify any version it names is current, before touching a file.


1. GROUND — establish the ferry (if needed), then one live snapshot

Rebuild every decision from current state. Cached branch labels, old chat summaries, and stale AGENTS.md/CLAUDE.md conclusions are not authority. This is also how you avoid the "multiple options / half-finished PR / preexisting implementation" confusion: read what is true now, not what something claims.

Establish the ferry per references/establish.md — read it once, on first entry only (and again only when an explicit PR redirects an existing ferry). It is the single "establish once" both solo entry points share, and it now also handles the fleet-lookout skip (a charon:lookout works its one assigned PR directly and writes no solo state file) and explicit-PR precedence (a PR the user names beats a pre-existing .claude/charon.local.md). Otherwise: if the state file already exists, read pr: from it; if not, resolve and write it there. Then take ONE live snapshot:

PR=<number>
gh pr view "$PR" --json number,title,state,isDraft,headRefName,baseRefName,headRefOid,baseRefOid,mergeable,mergeStateStatus,reviewDecision,statusCheckRollup,reviews,comments,autoMergeRequest,url
gh pr checks "$PR"            # ONE snapshot — never --watch
git fetch --all --prune --tags --quiet
git status --short --branch

Read the full file on GitHub · 236 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 236 lines · 134 tokens per session scan B e0d8e9739aa2

Subscribe to this mod's changes

charon is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 22d ago), licensed MIT. It adds 134 tokens to every session and 3,341 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

agent-merge-conflict-arbiter

Neutral arbiter for merge conflicts between two agents.

NousResearch/hermes-agent · 19 tokens

git-advanced-workflows

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

wshobson/agents · 54 tokens

bisect

Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.

chromium/chromium · 52 tokens

mantis-critic

Assesses the production viability of findings, filtering out debug-only features and assertion traps. Use when findings have been validated and you need to confirm they are triggerable in production release builds (with assertions disabled). Don't use for writing reproduction scripts or patches.

google/mantis · 55 tokens

hotpath_bump

Bump the hotpath version number across the workspace and related files. Updates crate versions in Cargo.toml files (exact patch version) and version references in the backend middleware, hotpathinit skill, and README (major.minor only). Use when the user wants to bump, bump the version, or release a new hotpath…

pawurb/hotpath-rs · 73 tokens

comet-github-issue-fix

A workflow for fixing a confirmed Comet-related GitHub issue or review blocker within an isolated scope. It covers matching the work to the relevant workflow, testing the change, checking runtime results, and preparing a careful handoff.

rpamis/comet · 71 tokens