parallel-autonomous-agents

A method for several unsupervised agents to work on one shared Git repository. Agents repeatedly claim tasks, implement them, test their work, and continue through a backlog while lock files prevent two agents from taking the same task.

In plain words
What is it for?
Use it to run multiple autonomous agents on a shared codebase, such as a long-running backlog or overnight build effort. It helps coordinate task ownership, testing, retries, and continued work.
Why use it?
It lets work continue without a person assigning every next task, while reducing collisions between agents editing the same project. Fresh sessions and machine-readable test results help keep progress controlled.

Skill for Claude CodeCodex

Part of the agent-stdlib plugin — 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers shipped together

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/hoja-solutions/agent-stdlib/parallel-autonomous-agents
Any agent
npx skills add Hoja-Solutions/agent-stdlib --skill parallel-autonomous-agents
Clone the repo
git clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlib

Made for: Claude Code, Codex.

Or install agent-stdlib, the plugin that ships this one along with the rest of its 14 skills, 2 commands, 1 agent, 2 hooks, 2 MCP servers.

Per session 183 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 855 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 $0.00183 $0.00855
Opus 5 $0.00092 $0.00428
Sonnet 5 $0.00037 $0.00171
Haiku 4.5 $0.00018 $0.00085

Measured 2d ago against content hash 790f9918ada8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-autonomous-agents 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.

skills/parallel-autonomous-agents/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel autonomous agents

Source: Building a C compiler with a team of parallel Claudes. The lock-file mechanism exists as a standalone framework (claude_code_agent_farm); the autonomy loop exists as other skills. No skill packages the two together for a shared git repo, and most skills coordinate by git worktree instead, which this contrasts against.

The goal is sustained parallel progress on one codebase with nobody watching. Several agents run at once, each claiming work, doing it, and moving to the next thing on its own. Two mechanisms make that safe: a loop that keeps each agent going, and a lock protocol that keeps them off each other's toes.

The autonomy loop

Each agent runs in a loop that picks the next task, does it, and respawns without pausing for a human. A simple shape is a script that calls a headless agent CLI (claude -p, opencode run, or any other) in a fresh container per session, so context never accumulates across tasks and a wedged session cannot poison the next. The loop is what turns a one-shot agent into one that works through a backlog overnight.

Lock files claim work

Coordinate through the repo itself. To take a task, an agent writes a lock file naming it, then works on an isolated clone:

  1. Claim by writing current_tasks/<task>.txt.
  2. Work on a private clone of the repo.
  3. Pull and merge upstream before pushing, so concurrent work integrates.
  4. Push the result.
  5. Remove the lock file.

Add stale-lock detection: if a lock is older than a threshold, assume the agent died and reclaim the task. Without it, one crash strands a task forever.

Lock files or worktrees

This is the fork worth naming, because most existing skills take the other branch. Worktree isolation gives each agent its own checkout and merges later; it suits agents that should never see a shared state mid-flight. Lock files keep the agents on one shared history with a visible claim registry, which suits a team grinding a backlog where you want one integrated line of work and cheap coordination. Choose lock files when the shared registry and single history are the point.

Read the full file on GitHub · 56 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 · 56 lines · 183 tokens per session scan A 790f9918ada8

Subscribe to this mod's changes

parallel-autonomous-agents is a skill published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 183 tokens to every session and 855 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.