solo

solo is a skill for Claude Code, Codex from dewil/claude-control. It costs 174 tokens per session (1,577 once invoked), scanned A, original, MIT.

A handoff skill that turns the current coding session into an independent background agent managed by claude-control. The agent continues the stated mission after you leave the session.

In plain words
What is it for?
Use it to hand off a clean Git project with a test, lint, build, or human review as its acceptance check. The resulting agent remains visible through the supervising system.
Why use it?
It lets longer tasks continue without keeping the session open, while requiring a clear way to check whether the work succeeded. It also prevents uncommitted work from being silently omitted.

Skill for Claude CodeCodex

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 skills/dewil/claude-control/solo
Any agent
npx skills add dewil/claude-control --skill solo
Clone the repo
git clone --depth 1 https://github.com/dewil/claude-control

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 solo

README.md
[![agentmods](https://agentmods.dev/badge/skills/dewil/claude-control/solo.svg)](https://agentmods.dev/skills/dewil/claude-control/solo)
Your own site
<a href="https://agentmods.dev/skills/dewil/claude-control/solo"><img src="https://agentmods.dev/badge/skills/dewil/claude-control/solo.svg" alt="Measured on agentmods" height="20"></a>
Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,577 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 $0.00174 $0.01577
Opus 5 $0.00087 $0.00788
Sonnet 5 $0.00035 $0.00315
Haiku 4.5 $0.00017 $0.00158

Measured 4d ago against content hash d844ba44ae02, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

solo 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.

.claude/skills/solo/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

solo

Передача текущей сессии в автономный полет. После handoff'а транскрипт сессии адоптируется в приватный namespace агента, reconciler поднимает ее в выделенном рантайме agent-<name> - с этой же памятью, тем же session_id, видимую с телефона. Приемку результата ставит внешний контур (reconciler/человек), не сам агент.

Пре-флайт (все проверки ДО регистрации; отказ - честный, с причиной)

  1. Платформа: command -v claude-rc && systemctl --user is-active claude-agent-reconciler.service - иначе "агентный слой не установлен".
  2. Git-проект: cwd внутри git-репо (git rev-parse --show-toplevel); vault'ы и не-git каталоги не передаются.
  3. Чистота дерева: git status --porcelain пуст. Иначе - предложи пользователю закоммитить/стэшнуть и остановись: worktree агента создается от HEAD, незакоммиченный WIP в миссию НЕ поедет - молча потерять его недопустимо.
  4. Проверяемый критерий приемки - без него /solo отказывает (принцип "автоматизируем только проверяемое"). Если критерий можно выразить детерминированной командой (тесты, линт, сборка) - он станет acceptance.check; если нет - приемка уйдет человеку (needs-human), об этом честно скажи.

Шаг 1: миссия

Собери из контекста разговора черновик миссии и покажи пользователю на подтверждение (без подтверждения не регистрируй):

# Миссия: <короткое имя>
## Цель
<что должно быть сделано, 1-3 предложения>
## Критерий приемки (проверяемый)
<команда или человекочитаемый критерий>
## Ограничения
<что нельзя трогать, лимиты>
## Стоп-условия
<когда остановиться и позвать человека>

Имя агента: kebab-case из цели, ^[a-z][a-z0-9-]{0,30}[a-z0-9]$.

Шаг 2: параметры handoff (механика, выполняй точно)

# session_id: nonce попадает в транскрипт немедленно (результат тула),
# grep по namespace-каталогу cwd находит НАШ файл
NONCE="solo-$RANDOM$RANDOM"; echo "$NONCE"
SLUG=$(pwd | sed 's|[^a-zA-Z0-9]|-|g')
SID=$(grep -l "$NONCE" "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/$SLUG/"*.jsonl | head -1 | xargs -n1 basename | sed 's/\.jsonl$//')

# PID процесса claude этой сессии: подъем по дереву от шелла тула
P=$$; while [[ -n "$P" && "$P" != 1 ]]; do
  case "$(ps -o comm= -p "$P")" in claude*|node*) CPID=$P; break;; esac
  P=$(ps -o ppid= -p "$P" | tr -d " ")
done
CSTART=$(awk '{print $22}' "/proc/$CPID/stat")

Read the full file on GitHub · 119 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 · 119 lines · 174 tokens per session scan A d844ba44ae02

Subscribe to this mod's changes

solo is a skill published in the GitHub repository dewil/claude-control (10 stars, last pushed 6d ago), licensed MIT. It adds 174 tokens to every session and 1,577 once invoked, about $0.0009 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 skills, from other repositories

clawdline

Use Clawdline to dispatch a bounded child task when the current Root keeps synthesis, integration, and landing; to hand off an existing work line for full continuation; or to send a message, report, status, finding, or coordination note to another live session. Triggers include "dispatch a task", "open a child…

sainteye/clawdline · 218 tokens

hermes-memory-github-sync

Set up automatic GitHub sync for Hermes Agent memory, skills, and config using git + macOS launchd. Runs every 30 minutes in the background. Covers repo init, .gitignore pitfalls, token extraction, and launchd plist setup.

itgoyo/hermes-skills · 57 tokens

hermes-memory-github-sync

Set up automatic GitHub sync for Hermes Agent memory, skills, and config using git + macOS launchd. Runs every 30 minutes in the background. Covers repo init, .gitignore pitfalls, token extraction, and launchd plist setup.

itgoyo/multica-skills · 57 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

openai-whisper-api

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

spinabot/brigade · 20 tokens

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…

vellum-ai/vellum-assistant · 90 tokens