A lease procedure for temporarily reserving a shared issue, path, process, or branch before writing to it. A lease records whether another session or automated job is using that resource and uses an exit code to allow or block work.

Use it before the first write to shared work, and renew, release, or verify the reservation as needed. Read-only work does not need one.

Multiple coding sessions, machines, or automated jobs can change the same resource at once and overwrite each other. A lease provides a visible coordination check instead of relying on informal conventions.

How Koroqe/OPOS configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/lease/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Koroqe/OPOS

Made for: Claude Code.

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/koroqe/opos/lease/github.svg)](https://agentmods.dev/skills/koroqe/opos/lease)

Your own site

<a href="https://agentmods.dev/skills/koroqe/opos/lease"><img src="https://agentmods.dev/badge/skills/koroqe/opos/lease/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/koroqe/opos/lease"><img src="https://agentmods.dev/badge/skills/koroqe/opos/lease.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 3,178 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	$0.03178
Opus 5.5	$0.00020	$0.01271
Sonnet 5.5	$0.00010	$0.00636
Haiku 4.5	$0.00005	$0.00318

Measured 27d ago against content hash 8e10807fc233, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lease 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 27d ago.

The scan reads SKILL.md. This mod also ships 13 executable files (lease.mjs, lib/claims.mjs, lib/claims.test.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/lease/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

lease

When to use

Before the first write to any shared area — where "shared" means anything another session could also be writing: a task issue, a folder, a scheduled process, a branch.

Read-only work needs no lease. A session that only reads takes nothing.

Why this exists

An OPOS company is written to by several actors at once: interactive sessions on different machines, scheduled jobs, CI bots, cloud routines. Before this skill, none of them could see what the others were doing, and the three signals that looked like occupancy each meant something else:

Signal	What it actually means
`.claude/.current-task`	Per-machine and gitignored. Bare issue numbers, no holder, no timestamp. Another machine cannot see it at all.
`assignee`	Ownership — who is accountable for the outcome. Not "who is touching this right now".
`Status: in_progress` in the issue body	Only set if someone passes `task-update --status`, through an unguarded read-modify-write.
A project-board column	Moved by a human, on their own schedule. Nothing in OPOS writes it.

The failure that follows is not exotic. Two agents write into the same folder and one commit buries the other's half-finished file. A session appends to a shared log while another is mid-run. A clone that has silently fallen behind serves scheduled jobs and reports success.

This skill makes occupancy a fact any actor can check, on any machine, in one call.

Inputs

--key — issue:<owner>/<repo>#<N> | path:<glob> | process:<name> | branch:<name>
--scope — comma-separated globs this holder may write (defaults to the glob for path: keys)
--intent — one line: what is being done. Mandatory for path:**.
--ttl — 45m, 2700s, 1h. Defaults per runtime; hard cap 4h without --long.

Setup

node .claude/skills/lease/lease.mjs init-ledger --create   # opens + pins the registry issue
node .claude/skills/lease/lease.mjs doctor                 # identity, clock, clone, ledger

Read the full file on GitHub · 200 lines

Files

What ships with it

16 files 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.

27d ago Changed · +37 lines 8e10807fc233
28d ago First seen · 163 lines · 51 tokens per session scan A e873be7a11cd

Subscribe to this mod's changes

lease is a skill published in the GitHub repository Koroqe/OPOS (4 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 3,178 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 2026-09-23.

Building agents Git and workflow concurrency framework github meta multi-session

OPOS: Skill for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

lease

When to use

Why this exists

Inputs

Setup

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

github-repository

github-account

github-subscriptions

github-release-management

github-multi-repo

github-pr-workflow