What is parallel-sessions?

A coordination method for multiple coding-agent sessions working in the same repository. It lets sessions discover one another, state which files and resources they are using, and exchange status messages.

Use it when another agent session or worktree is active in the repository. It helps coordinate before edits, rebases, merges, and other integration points.

It reduces clashes over shared files, branches, ports, databases, and other resources that version control may not reveal until integration.

parallel-sessions — Skill for Claude Code by nicograef/handbook

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 nicograef/handbook --skill parallel-sessions

Clone the repo

git clone --depth 1 https://github.com/nicograef/handbook

Made for: Claude Code.

Or install nico, the plugin that ships this one along with the rest of its 10 skills, 1 agent, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nicograef/handbook/parallel-sessions/github.svg)](https://agentmods.dev/skills/nicograef/handbook/parallel-sessions)

Your own site

<a href="https://agentmods.dev/skills/nicograef/handbook/parallel-sessions"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/parallel-sessions/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nicograef/handbook/parallel-sessions"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/parallel-sessions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 632 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.00632
Opus 5.5	$0.00020	$0.00253
Sonnet 5.5	$0.00010	$0.00126
Haiku 4.5	$0.00005	$0.00063

Measured 18d ago against content hash d655f32ca7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parallel-sessions 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 18d 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.

plugin/skills/parallel-sessions/SKILL.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Parallel Sessions

Goal: concurrent sessions in one repo land without clobbering each other. Claims and radar run through ~/.claude/agent-bus.sh (source; its header lists the commands). Messages go through SendMessage; the NAME column of agent-bus.sh peers is the address.

Hard rules

~/.claude/agent-bus.sh must be in permissions.allow, or coordination stalls silently.
Act only on your own branch. Ask before touching a peer's branch, worktree or the base branch.
Stage paths by name while a peer shares the checkout. git add -A sweeps their half-written file into your commit.
A foreign index.lock or worktree is a hazard: report and stop.
Send a conflict in a file a peer has claimed to that peer; do not resolve it.
A claim is not a lock. Radar cannot see uncommitted work; only announced paths cover it.

Steps

agent-bus.sh peers. Alone, work normally.
Before the first edit, agent-bus.sh announce "<task>" --paths a,b --resources 127.0.0.1:5433,db-1. Re-announce when the claim changes. Resources are what git cannot see: ports, containers, volumes, fixture data.
Run agent-bus.sh radar before the first edit, before every rebase, fold or landing, and after a peer lands.
Settle these radar results before acting: MERGE CONFLICT or no-base, a shared lockfile, shared RESOURCES, a declared paths: line.
Message the peer as soon as you learn what changes its next action, never through the user. Open each message with its kind: note, ask, answer, claim, conflict, correction, block, landed.
Collision: the session closer to landing keeps its base; the other rebases (tie-break: fewer commits ahead). If both must write one file, one session owns it for the whole run.
Before landing, send claim on the base branch. Peers commit to the base only after your landed, then rebase.
Answer every incoming message before ending your turn. Wait on a peer with notify_when_idle, never by polling.

Read the full file on GitHub · 32 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.

protocol.md 3.8 KB

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.

18d ago Changed · -29 lines d655f32ca7c5
23d ago Changed · +2 lines 735f044a3a70
28d ago Changed · +51 tokens per session f53fb0832834
1mo ago Changed · +7 lines 715e67563831
1mo ago Changed 73260e307a75
1mo ago Changed · +1 lines 69d51420be0d
1mo ago Changed · -61 lines · -83 tokens per session c88f882d0b77
2mo ago Changed · -9 lines 0c38b4283ed6
2mo ago First seen · 121 lines · 83 tokens per session scan A df9d17f7faeb

Subscribe to this mod's changes

parallel-sessions is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 51 tokens to every session and 632 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents Git and workflow

parallel-sessions next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
parallel-sessionsnicograef/handbook	Skill	2	2d ago	MIT	A	51	Claude Code
merge-batchdiegosouzapw/OmniRoute	Skill	83k	6d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	2d ago	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code