agentmods.dev

lane-contract

lane-contract is a skill for Claude Code from VKirill/claude-lane-stack. It costs 65 tokens per session (1,855 once invoked), scanned A, original, MIT.

A file-based task contract system for describing coding tasks in YAML, including which files a task owns and how it must be checked.

In plain words
What is it for?
Use it to write or review task YAML, define file ownership, set acceptance requirements, and run checks at writer, lane, or project level.
Why use it?
It prevents parallel tasks from editing the same files and makes acceptance checks explicit before work is dispatched.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions Codex.

Part of the lane-stack plugin — 53 skills, 4 commands, 17 agents, 1 hook shipped together

not rated 115repo +1 today A scan SkillSpector: pass 65 tokens original MIT

Good fit Use it to write or review task YAML, define file ownership, set acceptance requirements, and run checks at writer, lane, or project level.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vkirill/claude-lane-stack/lane-contract
View source ↗ VKirill/claude-lane-stack
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 VKirill/claude-lane-stack --skill lane-contract
Clone the repo
git clone --depth 1 https://github.com/VKirill/claude-lane-stack

Made for: Claude Code.

Or install lane-stack, the plugin that ships this one along with the rest of its 53 skills, 4 commands, 17 agents, 1 hook.

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 lane-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/lane-contract/github.svg)](https://agentmods.dev/skills/vkirill/claude-lane-stack/lane-contract)
Your own site
<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/lane-contract"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/lane-contract/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 lane-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/vkirill/claude-lane-stack/lane-contract"><img src="https://agentmods.dev/badge/skills/vkirill/claude-lane-stack/lane-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,855 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00065 $0.01855
Opus 5 $0.00032 $0.00928
Sonnet 5 $0.00013 $0.00371
Haiku 4.5 $0.00006 $0.00186

Measured 9d ago against content hash ef41b507a961, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

lane-contract 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 9d 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.

plugins/lane-stack/skills/lane-contract/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lane contract (files only)

Info (print and stop)

If $ARGUMENTS is info, or the user says info / справка / как запускать this skill: print the block below verbatim (Russian), then stop. Do not write task YAML.

lane-contract — контракт задачи (YAML в .agents/runs/)

Когда
- Оркестратор заполняет tasks после «делай».
- Проверка owns_paths / verification / acceptance.

Как открыть шпаргалку
- /lane-stack:lane-contract info
- каталог: /lane-stack:info
- раны целиком: /lane-stack:orchestrator-lanes info

PM до dispatch
1) run-init → PLAN/SPEC/tasks
2) owns_paths + never_touch + acceptance (поведение, не «всё зелёное»)
3) Одна задача = один product outcome. depends_on только compile/data.
4) Parallel только при disjoint owns.
5) run-validate --phase pre-dispatch
6) Один run-supervisor. lane = adoc main_write.

Писатель
- Только owns_paths. Не `.agents` (`run-validate` rejects it — sandbox remounts `.agents` read-only). Не merge/push main.
- L0 — узкие проверки. Вне owns сломалось → Gaps, не «починить мир».

Тиры
- L0 writer  · L1 lane-ctl verify  · L2 PM/CI

Нельзя
- timeout_sec в плане выдумывать (дефолт 900)
- verification[].command на файл, которого нет в cwd/worktree
- node_modules / кэши в owns
- мутировать YAML после первого старта

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

Orchestrator must

  1. run-init → fill PLAN/SPEC/tasks → run-validate --phase pre-dispatch before dispatch.
  2. Set owns_paths, never_touch, behavioral acceptance.
  3. Paste real interfaces into interfaces; declare read_first, invariants, out_of_scope, expected_outputs.
  4. One run-supervisor per run; lane-supervisor only for typed one-shots.
  5. Parallel only with disjoint owns_paths.
  6. Controller: owns → L1 verify → accept progressively.
  7. Task YAML immutable after first start.
  8. Pre-merge validate → merge main (PM only).
  9. Writers via durable controller (kimi/…); Codex write = recovery only.
  10. Separate provider vs verification pools.
  11. Decompose per orchestrator-lanes (one outcome per task; unlock ≠ feature).
  12. SPEC.md is real content when score ≥ 7 or ≥ 2 tasks (not the template stub).

Read the full file on GitHub · 178 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. 9d ago First seen · 178 lines · 65 tokens per session scan A ef41b507a961

Subscribe to this mod's changes

lane-contract is a skill published in the GitHub repository VKirill/claude-lane-stack (115 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,855 once invoked, about $0.0003 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 2026-08-30.

Claude CodePlanningProject managementagentic-codingai-agentsai-codingautomationclaude
Related

Other skills, from other repositories

swarm-plan

Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.

ZaxbyHub/opencode-swarm · 32 tokens

loop

Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…

ZaxbyHub/opencode-swarm · 72 tokens

issue-ingest

Full execution protocol for MODE: ISSUEINGEST -- GitHub issue intake, localization, spec generation, and transition to the full fix workflow.

ZaxbyHub/opencode-swarm · 33 tokens

issue-triage

3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.

FlorianBruniaux/claude-code-ultimate-guide · 81 tokens

phase-wrap

Claude Code adapter for MODE: PHASE-WRAP. Delegates to the canonical opencode-swarm phase boundary protocol.

ZaxbyHub/opencode-swarm · 0 tokens

production-scheduling

You are a senior production scheduler at a discrete and batch manufacturing facility operating 3–8 production lines with 50–300 direct-labor headcount per shift. You manage job sequencing, line balancing, changeover optimization, and disruption response across work centers that include machining, assembly, finishing…

loulanyue/awesome-claude-notes · 3 tokens