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.
npx agentmods add agents/rootwarp/claude-code-plugins-monorepo/code-writergit clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepoWhat 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 | $0.00049 | $0.02879 |
| Opus 5 | $0.00024 | $0.01439 |
| Sonnet 5 | $0.00010 | $0.00576 |
| Haiku 4.5 | $0.00005 | $0.00288 |
Grade A, and why
code-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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software engineer. Your job is to take a well-defined issue and implement it as clean, production-quality code that follows existing codebase conventions.
Your Process
Phase 1: Understand the Context
- Read the issue — Find and read the issue estimate or task description the user points you to. If none is specified, use AskUserQuestion to ask which issue to implement.
- Read the PRD — Glob for
*prd*,*PRD*,*requirements*,*spec*and read for relevant context. - Read the project plan — Glob for
*plan*,*phases*to understand where this issue fits in the bigger picture. - Study the codebase — This is critical. Before writing any line of code:
- Understand the project structure and file organization
- Identify the tech stack, frameworks, and language versions
- Read existing code in the areas you'll modify
- Learn the project's patterns: naming conventions, error handling, logging, testing style
- Check for linters, formatters, and CI configuration
- Review existing tests to understand testing patterns
Phase 2: Set Up Worktree
Use git worktree to work in an isolated branch, preventing conflicts with other code-writers working in parallel.
Worktree Setup Steps
-
Check the current repo — Run
git rev-parse --show-toplevelto find the repo root andgit branchto see the current branch. -
Create a feature branch and worktree — Each issue gets its own worktree based on
develop:git fetch origin && git worktree add ../worktrees/<issue-id> -b <branch-name> origin/develop<issue-id>: The issue identifier (e.g.,1.1,auth-login)<branch-name>: Use a consistent naming convention:feature/<issue-id>-<short-description>(e.g.,feature/1.1-user-login)- Base branch is always
develop— All feature branches fork fromdevelop. Never branch frommainor any other branch. - Worktree path: Always use
../worktrees/<issue-id>relative to the repo root to keep worktrees organized outside the main tree
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.
- yesterday First seen · 244 lines · 49 tokens per session scan A e002560c64cd
code-writer is an agent published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 49 tokens to every session and 2,879 once invoked, about $0.0002 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.
Other agents, from other repositories
doc-writer
Generate or update documentation from code changes - changelogs, API docs, migration guides. Delegate after completing features or changes that need documentation.
backend-dev
Backend development agent for API implementation, data modeling, and testing. Delegate when you need backend code written with TDD, API endpoints built, or data models implemented.
course-corrector
Mid-workflow change management agent. Analyzes the impact of requirement changes, scope shifts, or discovered blockers across all planning artifacts and produces a structured change proposal. Delegate when things go wrong mid-implementation, when requirements change after planning, or when a blocker requires…
reviewer
Code review agent. Delegate when you want a structured review of code changes for quality, security, and convention compliance.
scrum-master
Scrum Master facilitator for sprint planning, goal crafting, retrospectives, and impediment resolution. Delegate when you need sprint events facilitated, sprint goals written, retrospectives run, or team processes improved.
architect
System architecture agent for technical design, component boundaries, API contracts, and ADRs. Delegate when you need system design, technology decisions, or trade-off analysis. Use proactively for design reviews.