repository-manager-lane-lifecycle

repository-manager-lane-lifecycle is a skill for Claude Code, Codex from Knuckles-Team/repository-manager. It costs 156 tokens per session (2,748 once invoked), scanned A, original, MIT.

A workflow for one person or coding agent to work safely in an isolated part of a shared repository. A worktree is a separate working folder connected to the same version-control project; a lane is one worker’s branch and workspace.

In plain words
What is it for?
Use it to open, check, diagnose and close an isolated work lane, especially when builds fail unexpectedly, work disappears or several workers edit the same repository.
Why use it?
It prevents concurrent workers from overwriting files, tests or build state that another worker is using.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/uv_workspace.py run --all-extras -- pytest <args>.

Good fit Use it to open, check, diagnose and close an isolated work lane, especially when builds fail unexpectedly, work disappears or several workers edit the same repository.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Knuckles-Team/repository-manager
agentmods
npx agentmods add skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle

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 repository-manager-lane-lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle/github.svg)](https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle)
Your own site
<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle/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 repository-manager-lane-lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle"><img src="https://agentmods.dev/badge/skills/knuckles-team/repository-manager/repository-manager-lane-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,748 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00156 $0.02748
Opus 5 $0.00078 $0.01374
Sonnet 5 $0.00031 $0.00550
Haiku 4.5 $0.00016 $0.00275

Measured 10d ago against content hash 3ed007f198b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

repository-manager-lane-lifecycle 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 10d 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.

repository_manager/skills/repository-manager-lane-lifecycle/SKILL.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Manager — Lane Lifecycle

A lane is one worker — one agent session or one person — working one repository in one worktree on one branch. Dozens of lanes run concurrently here.

Every collision this workspace has actually suffered has one shape:

A background or global actor mutates state a lane assumed it owned.

This skill is the working pattern that keeps lanes from destroying each other's work. It is not advice: each rule below has a check behind it in repository_manager/lane_doctor.py, and every check exists because a specific incident destroyed real work while the rule that would have prevented it was written down, in prose, in front of the actor who broke it.

When to use

  • You are about to edit a repository other lanes are also editing. Start here.
  • A test fails in a way that cannot be true; a build will not go green; a merge keeps being refused; work you wrote has vanished. Run doctor first, before debugging the code — it answers in under a second.
  • You are finishing a piece of work and want it landed.

When NOT to use

  • Landing, gating, conflict resolution, reconciling a moved base → repository-manager-merge-and-reconcile.
  • Sweeping many repositories at once, bulk worktree creation, workspace audits → repository-manager-fleet-scale-operations.
  • Raw worktree verbs with no lifecycle around them → repository-manager-worktree-orchestration.

The four arbitration classes

Every shared resource belongs to exactly one class, and each class has exactly one mechanism. The classification is data, not code, in agent_utilities/governance/lane_resources.yaml — adding a resource is a row, never a new mechanism. Read it with agent-utilities lane classify.

Class Rule Mechanism
PARTITION Stop sharing it — take your own instance. repository-manager --lane env / agent-utilities lane env
APPEND-ONLY Stop rewriting it — append to your own fragment; a reconciler folds fragments into one generated view. FragmentStore / scripts/deferred_registry.py open
LEASE Announce, then defer. Exit 75 means another lane holds it. agent-utilities lane lease
READ-ONLY Do not mutate it at all. agent-utilities lane guard

Read the full file on GitHub · 241 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. 10d ago First seen · 241 lines · 156 tokens per session scan A 3ed007f198b6

Subscribe to this mod's changes

repository-manager-lane-lifecycle is a skill published in the GitHub repository Knuckles-Team/repository-manager (2 stars, last pushed 13d ago), licensed MIT. It adds 156 tokens to every session and 2,748 once invoked, about $0.0008 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