Agent skill

Lane Contract

File-based task contracts under .agents/runs/ with ownspaths, verification tiers L0/L1/L2, and solo merge rules.

Install Lane Contract

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .claude/skills/lane-contract && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .claude/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .agents/skills/lane-contract && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .agents/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .cursor/skills/lane-contract && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .cursor/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/VKirill/claude-lane-stack.git --path plugins/lane-stack/skills/lane-contract

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .gemini/skills/lane-contract && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .gemini/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .github/skills/lane-contract && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .github/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add VKirill/claude-lane-stack --skill lane-contract -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install VKirill/claude-lane-stack lane-contract --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/VKirill/claude-lane-stack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/lane-stack/skills/lane-contract .opencode/skills/lane-contract && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "lane-contract" agent skill from https://github.com/VKirill/claude-lane-stack/tree/main/plugins/lane-stack/skills/lane-contract into .opencode/skills/lane-contract/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lane-contract", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: lane-contract
GitHub stars: 122
Token cost: ~2.3k tokens
SKILL.md length: 1,015 words
Files: 2 (incl. references)
Skills in repo: 49
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

File-based task contracts under .agents/runs/ with ownspaths, verification tiers L0/L1/L2, and solo merge rules.

Works in 12 steps: run-init → fill PLAN/SPEC/tasks →… → Set owns_paths, never_touch, behavioral… → read_first: existing project-relative… → …
Reviewing task YAML / the task-v2 contract (Lane Pilot plan)
SKILL.md covers Info, Orchestrator must, Authoring checklist (before… and Lane must (writer), plus 4 more sections
Calls npm and git

What it does

Lane Contract is an agent skill from VKirill/claude-lane-stack. File-based task contracts under .agents/runs/ with ownspaths, verification tiers L0/L1/L2, and solo merge rules. Use when authoring or reviewing task YAML / the task-v2 contract (Lane Pilot plan), ownspaths, acceptance, or verification commands; $ARGUMENTS exactly info prints the card.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/info.md`).

It sits in Agent Workflows. The repository describes itself as: Multi-agent AI coding factory for one person — Claude Code PM + Codex/Qwen/Grok/Kimi/AGY writers, durable conveyor, auto-merge to main. The licence is MIT.

When your agent uses it

Reviewing task YAML / the task-v2 contract (Lane Pilot plan)
Verification commands
$ARGUMENTS exactly info prints the card

Example prompts

“/lane-contract”

Workflow steps

12 steps, taken from the first numbered list in SKILL.md.

run-init → fill PLAN/SPEC/tasks → run-validate --phase pre-dispatch before dispatch.
Set owns_paths, never_touch, behavioral acceptance.
read_first: existing project-relative files only. Line windows go in context_selectors. interfaces: signatures/types, or []. Product…
One run-supervisor per run; lane-supervisor only for typed one-shots.
Parallel only with disjoint owns_paths.
Controller: owns → L1 verify → accept progressively.
Task YAML immutable after first start.
Pre-merge validate → merge main (PM only).
Writers via durable controller (kimi/…); Codex write = recovery only.
Separate provider vs verification pools.
Decompose per orchestrator-lanes references/decomposition.md (one outcome per task; unlock ≠ feature).
SPEC.md is real content when score ≥ 7 or ≥ 2 tasks (not the template stub).

What it can do on your machine

Read from SKILL.md and the folder at commit 45fa19e. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- npm
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Lane Contract loads about 2.3k tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 1,015 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~77
When it runs · the whole SKILL.md, loaded when a task matches: ~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:92

ch` | Owns gate | Secrets / unrelated | `.env*` minimum |

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from VKirill/claude-lane-stack at commit 45fa19e, republished under its MIT licence (© VKirill). 1,015 words, ~2,255 tokens.

Download SKILL.mdSave it as .claude/skills/lane-contract/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: lane-contract
description: File-based task contracts under .agents/runs/ with owns_paths, verification tiers L0/L1/L2, and solo merge rules. Use when authoring or reviewing task YAML / the task-v2 contract (Lane Pilot `plan`), owns_paths, acceptance, or verification commands; `$ARGUMENTS` exactly info prints the card.
argument-hint: [info]

Lane contract (files only)

Inside a Lane Pilot chat (LANE_PILOT_AGENT_TYPE set / tools lane_pilot_* present) the contract is the task-v2 JSON in the plan of lane_pilot_dispatch_writer, and its schema is strict: exactly schema_version, id, title, risk, lane, project_cwd, read_first, interfaces, invariants, out_of_scope, expected_outputs, owns_paths, never_touch, depends_on, objective, acceptance, verify, verification[{command, cwd, timeout_sec?}] (timeout_sec up to 7200). Any other field (context_selectors, impact_*, skills) makes Lane Pilot reject the whole contract: put line windows in objective or interfaces as path:start-end. The writer RUNS verification and Lane Pilot re-runs it at acceptance, so every task needs real verification commands. Lane Pilot owns run state; run-init, run-validate --phase, lane-ctl, run-supervisor, the L0 rule «writer does not run tests» and lane = adoc main_write below are the terminal Lane Stack harness.

Info

If $ARGUMENTS is exactly info, print references/info.md verbatim (Russian), then stop. Do not write task YAML.

Canonical: FILE-CONTRACT.md, SOLO-ORCHESTRATION.md, docs/decisions/ADR-codex-effort.md, skill orchestrator-lanes (references/decomposition.md).

Orchestrator must

run-init → fill PLAN/SPEC/tasks → run-validate --phase pre-dispatch before dispatch.
Set owns_paths, never_touch, behavioral acceptance.
read_first: existing project-relative files only. Line windows go in context_selectors. interfaces: signatures/types, or []. Product invariants / out_of_scope; never writer recovery. expected_outputs: artifact path, not “tests green”.
One run-supervisor per run; lane-supervisor only for typed one-shots.
Parallel only with disjoint owns_paths.
Controller: owns → L1 verify → accept progressively.
Task YAML immutable after first start.
Pre-merge validate → merge main (PM only).
Writers via durable controller (kimi/…); Codex write = recovery only.
Separate provider vs verification pools.
Decompose per orchestrator-lanes references/decomposition.md (one outcome per task; unlock ≠ feature).
SPEC.md is real content when score ≥ 7 or ≥ 2 tasks (not the template stub).

Authoring checklist (before pre-dispatch)

Decomposition

Each task id has one product outcome
depends_on is a real compile/data edge, not narrative order
Large delete vs new algorithm are separate tasks
Parallel tasks have disjoint owns

Owns completeness

Every path the objective requires editing is listed (including companion modules the prompt forces — e.g. quality gates that still reference a removed field)
Package caches, node_modules, .npm-cache, build caches are never in owns
never_touch covers secrets, prisma (if frozen), unrelated products

Verification (L1)

Commands are path-scoped unit/typecheck for this task
No bare monorepo npm run build / root npm test on multi-task runs (that is L2)
timeout_sec — omit. Runtime defaults to 900s. Do not invent or bike-shed timeouts in plans
Every script path in verification[].command exists on disk under verification[].cwd before pre-dispatch
If project_cwd is a worktree: do not assume main-repo .agents/runs/... is visible — write/copy check.py into the worktree path or put tests under product tests/ in owns; absolute paths to main are rejected
Prefer product tests (tests/test_*.py) over .agents/**/check.py when possible
PM may Write only basename check.py under .agents/runs/<slug>/[artifacts/<id>/] (guard allowlist); not other .py, not state.json/reports

Acceptance

Observable behavior, not “all packages green”
Matches objective; greps/sweeps named when deletion tasks

Lane must (writer)

Read the complete raw task YAML supplied in the prompt; open TASK_FILE if absent or uncertain.
Work only in PROJECT_CWD.
Edit only owns_paths. Honor never_touch.
Do not write .agents.
Do not run tests/typecheck/verification[]; L1 is lane-ctl verify. Report in English.
No git merge/push main.
Outside-owns build break → report Gaps, do not “fix the world”.
Do not run monorepo suites or Worker checks.

Show full SKILL.md (476 more words)Show less

Required schema-v2 task fields

Identity (must match adoc / run): schema_version, id, title, risk, lane, project_cwd.

Field	What the machine uses	Fill	Leave empty / omit
`objective`	Writer TZ (prompt)	One product outcome, behavior	never
`acceptance`	Report + PM	Observable behavior	never
`owns_paths`	Owns gate	Every path the outcome must edit	never
`never_touch`	Owns gate	Secrets / unrelated	`.env*` minimum
`read_first`	Packet files	Existing files, no notes	`[]` if none
`context_selectors` (terminal only)	Packet line windows	`{path, start_line, end_line}`	omit (do not put windows in `read_first`)
`verification`	L1 `lane-ctl verify`	Focused commands	`[]` only with `verify: none`
`verify`	Schema only	`tests` / `smoke` / `none` matching L1	do not invent a second suite
`depends_on`	DAG	Real compile/data ids	`[]`
`interfaces`	Prompt + path scrape	Signatures / type names	`[]`
`invariants`	Prompt	Product constraints	`[]`
`out_of_scope`	Prompt	Non-goals not already in `never_touch`	`[]`
`expected_outputs`	Schema + prompt	Artifact path this task creates	one path, not “typecheck green”
`impact_receipt` / `impact_targets` (terminal only)	Packet	Only if you captured a receipt	omit
`skills` (terminal only)	Claude prompt inject	`impeccable-ui` on UI tasks	omit (OpenCode ignores)

run-validate --phase pre-dispatch rejects: git checkout/restore in the YAML; read_first prose (section C4, lines 10-20); missing read_first files; CONTINUATION / Gaps / HARD RULE / wc -l / edit-tool recovery in interfaces or invariants.

No mutable status / free-form verify strings on new runs.

Prepared execution context

lane-ctl supplies hashes and path pointers from read_first and context_selectors. Paths named in interfaces/objective (file.ts:12-40) become interface_refs. Keep related tests in read_first as paths. The original task remains immutable. OpenCode already loads lane-writer; the user prompt is YAML + packet, not a second copy of the writer contract.

Writers reuse unchanged supplied code. Omit impact_receipt unless the file exists on disk.

Verification tiers

Tier	Who	What
L0	Writer	Code + test files; do not execute runners
L1	`lane-ctl verify`	Task `verification[]` only
L2	PM / CI	One full or affected suite per run

Worktree + pre-authored checkers

verification.cwd must equal the task worktree/project_cwd. Relative scripts resolve inside that tree. Main checkout .agents/runs/<slug>/artifacts/001/check.py is not the same file as
worktree/.agents/runs/<slug>/artifacts/001/check.py.

Before run-validate --phase pre-dispatch / controller start:

Pre-author the checker (recovery/PM — not the writer).
Place it under the worktree at the path the command uses.
Or use in_place workspace so one .agents tree is enough.

run-validate fails closed if the script file is missing.

`verify` levels

Level	Meaning
none	Trivial / visual
smoke	Single cheap command
tests	Focused automated tests (not monorepo green)

Owns / dirt / caches

Class	Policy
Pre-existing dirt outside owns	Foreign ignored (baseline / no-baseline policy)
New product files outside owns	Fail (writer leak or missing owns entry)
`.npm-cache`, `node_modules`, pnpm/yarn/turbo caches	Ignored by gate — never put in owns
`never_touch` hits (new)	Fail

If owns fails with only cache paths: treat as control-plane noise, not “expand owns”.

SPEC.md contract (run level)

When required (score ≥ 7 or ≥ 2 tasks), SPEC must state goal, interfaces, invariants, out of scope, definition of done — in English, not the run-init stub. run-validate --phase pre-dispatch rejects stubs.

Files

SKILL.md and 1 other file (references) in plugins/lane-stack/skills/lane-contract of VKirill/claude-lane-stack.

SKILL.md
references/info.md

Open the folder on GitHubat commit 45fa19e

Compare with similar skills

Lane Contract next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Lane Contract compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Lane Contract this skillVKirill/claude-lane-stack	122	—	~2.3k	Automated safety check: Notes	MIT	yesterday
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	today
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official	38k	10 repos	~4.1k	Automated safety check: Notes	Apache-2.0	today
Using Superpowersfarm-fe/farm	5.6k	35 repos	~1.4k	Automated safety check: Pass	MIT	18 days ago
Executing Plans Inlineobra/superpowers	297k	2 repos	~5.1k	Automated safety check: Pass	MIT	today
Skill CreatorAzure/azqr	796	89 repos	~8.2k	Automated safety check: Pass	Apache-2.0	yesterday

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
Hook Development for Claude Code Plugins
anthropics/claude-plugins-official
Official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
38k GitHub starsUsed in 10 repos~4.1k tokens
Agent WorkflowsAuto-check: notes
Using Superpowers
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
5.6k GitHub starsUsed in 35 repos~1.4k tokens
Agent WorkflowsAuto-check passed
Executing Plans Inline
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
297k GitHub starsUsed in 2 repos~5.1k tokens
Agent WorkflowsAuto-check passed
Skill Creator
Azure/azqr
Official
Create new skills, modify and improve existing skills, and measure skill performance.
796 GitHub starsUsed in 89 repos~8.2k tokens
Agent WorkflowsAuto-check passed
Claude Code Agent Development
anthropics/claude-plugins-official
Official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
38k GitHub starsUsed in 7 repos~2.8k tokens
Agent WorkflowsAuto-check passed

Questions about Lane Contract

What does Lane Contract do?

File-based task contracts under .agents/runs/ with ownspaths, verification tiers L0/L1/L2, and solo merge rules. Lane Contract is an agent skill from VKirill/claude-lane-stack.agents/runs/ with ownspaths, verification tiers L0/L1/L2, and solo merge rules.

When should I use Lane Contract?

Lane Contract fits situations like: reviewing task YAML / the task-v2 contract (Lane Pilot plan); verification commands; $ARGUMENTS exactly info prints the card.

How do I install Lane Contract in Claude Code?

Run `npx skills add VKirill/claude-lane-stack --skill lane-contract -a claude-code`. Or copy the skill folder (plugins/lane-stack/skills/lane-contract in VKirill/claude-lane-stack) into .claude/skills/lane-contract in your project. Claude Code loads it when a task matches its description.

How do I install Lane Contract in Codex?

Run `npx skills add VKirill/claude-lane-stack --skill lane-contract -a codex`. Or copy the skill folder (plugins/lane-stack/skills/lane-contract in VKirill/claude-lane-stack) into .agents/skills/lane-contract in your project. Codex loads it when a task matches its description.

Can I use Lane Contract in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add VKirill/claude-lane-stack --skill lane-contract -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lane-contract, .gemini/skills/lane-contract, .github/skills/lane-contract and .opencode/skills/lane-contract in your project.

What does Lane Contract need to run?

Going by SKILL.md and its folder, Lane Contract needs the command-line tools its instructions call (npm and git).

Does Lane Contract access the network?

SKILL.md contains no URLs. Its commands use npm and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Lane Contract safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Lane Contract use?

Lane Contract is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lane Contract use?

About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 397 tokens, read only when the agent opens those files.

What are the alternatives to Lane Contract?

Skills that share tags, products or a category with Lane Contract: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lane Contract?

VKirill (a GitHub user) maintains it in VKirill/claude-lane-stack, which has 122 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 9, 2026.

Source: VKirill/claude-lane-stack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Lane Contract

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Lane contract (files only)

Info

Orchestrator must

Authoring checklist (before pre-dispatch)

Decomposition

Owns completeness

Verification (L1)

Acceptance

Lane must (writer)

Required schema-v2 task fields

Prepared execution context

Verification tiers

Worktree + pre-authored checkers

verify levels

Owns / dirt / caches

SPEC.md contract (run level)

Files

Compare with similar skills

Similar skills

More from VKirill/claude-lane-stack

Related

Questions about Lane Contract

`verify` levels