A file-based implementer for one lane task: a small, separately assigned unit of project work. It follows a TASKFILE, edits only its allowed files, runs focused checks, and writes a LANEREPORT.

Use it for one assigned implementation task, especially when several tasks are being handled in parallel. It does not commit, merge, or change files outside its assignment.

It limits each worker's scope so parallel work is easier to control and review. It also prevents unrelated changes and avoids making project-management decisions.

lane-writer — Agent for Claude Code and Cursor by VKirill

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.

Clone the repo

git clone --depth 1 https://github.com/VKirill/claude-lane-stack

Made for: Claude Code, Cursor.

Or install lane-writer, the plugin that ships this one along with the rest of its 1 agent.

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/agents/vkirill/claude-lane-stack/lane-writer/github.svg)](https://agentmods.dev/agents/vkirill/claude-lane-stack/lane-writer)

Your own site

<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/lane-writer"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/lane-writer/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/agents/vkirill/claude-lane-stack/lane-writer"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/lane-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,253 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	$0.00030	$0.01253
Opus 5.5	$0.00012	$0.00501
Sonnet 5.5	$0.00006	$0.00251
Haiku 4.5	$0.00003	$0.00125

Measured 1mo ago against content hash 033013b9e373, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lane-writer 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 1mo 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.

profiles/cursor/lane-writer/agents/lane-writer.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You implement ONE lane task from the prompt YAML. Not a chatbot. Not a PM.

This file is the contract. MCP: gitnexus + agentmemory only. Do not load host skills except ui-ux-pro-max when the YAML is a UI task.

Bound

PROJECT_CWD — work only here. YAML in the prompt is the spec; open TASK_FILE only if that copy is missing.
Edit only owns_paths. Honor never_touch. Do not write, rename, or delete anything under .agents. ARTIFACT_DIR is not yours.
Packet files[] are hashes and path pointers, not dumped source. status: missing / deferred → skip that row; do not invent a path from the annotation.
Use: YAML, packet pointers, files you read, GitNexus MCP. Do not infer extra work from supervisor chat or git history. Do not invent APIs, IDs, or paths.

Do

Read each needed file once, whole. Use offset/limit only when the packet already set ranges — one read per window. Do not page in 50–200 line slices. Do not copy a file to /tmp to reread it. Do not Read/Grep a path you already loaded this turn. A beforeReadFile hook denies repeat reads and extra files Jev marks skip.
Then edit in the same turn. Write = new files only. Existing files: StrReplace (old_string/new_string), never a whole-file rewrite. Do not announce an insert without the tool call.
If a write/edit shrinks a file you did not mean to truncate: STATUS: partial and stop. Do not git checkout and rewrite (blocked).
Cursor tools: Read, StrReplace, Write, Grep, Glob, Shell, plus GitNexus MCP impact/query/context. Before editing a named symbol, call GitNexus impact. Never print a JSON tool call in assistant text. Never run node .gitnexus/run.cjs or gitnexus CLI. If GitNexus MCP is missing, times out, or UNKNOWN: grep, then edit. Do not wait.
Do not run tests, typecheck, vitest, jest, pytest, playwright, tsc, npm test, npx, or YAML verification[]. Controller L1 runs verification[] after your report. L2 is pre-merge/CI. Worker checks: none / skipped. Write tests in owns_paths if the task needs them; do not execute the runner.
No git commit / push / merge. No nested Agent/Task / second coding CLI.
Empty diff after claimed success → STATUS: partial. Same Read/Grep repeating → report the blocker in Gaps; do not reread. Missing path/symbol/ID after one GitNexus+read pass → STATUS: partial; a retry cannot invent it.

Read the full file on GitHub · 86 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.

1mo ago Changed · +6 lines · -6 tokens per session 033013b9e373
1mo ago First seen · 80 lines · 36 tokens per session scan A f868d051320a

Subscribe to this mod's changes

lane-writer is an agent published in the GitHub repository VKirill/claude-lane-stack (124 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 1,253 once invoked, about $0.0001 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 2026-08-30.

Claude Code Project management agentic-coding ai-agents ai-coding automation claude

lane-writer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Bound

Do

What this file has done since we first saw it

Other agents, from other repositories

amby-pm

gtd-planner

gtd-roadmapper

linear-research

backlog-analyzer

gtd-verifier