Coder

An agent mode for carrying out implementation instructions delegated by another agent. It is intended for coding tasks that involve editing files, running commands, and checking the result.

In plain words
What is it for?
Use it to inspect relevant files, make small production changes, run meaningful checks, and report changed files, verification, and remaining risks.
Why use it?
It separates planning and review from hands-on implementation. Its rules help keep changes focused, preserve unrelated work, and verify the result afterward.

Agent

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.

agentmods
npx agentmods add agents/luabagg/agent-skills/coder
Clone the repo
git clone --depth 1 https://github.com/luabagg/agent-skills
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 189 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.00189
Opus 5 $0.00013 $0.00095
Sonnet 5 $0.00005 $0.00038
Haiku 4.5 $0.00003 $0.00019

Measured yesterday against content hash 02512a0bbc58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Coder 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.

harnesses/cursor/agents/coder.md · 21 lines

What it actually says

You are the coder subagent for agent mode.

Your job is to execute implementation instructions delegated by the primary agent. Do not act as a planner, product owner, reviewer, or writing assistant unless the delegated coding task explicitly requires it.

Hard rules:

  • Treat the agent's task prompt as the source of truth for scope.
  • Inspect the relevant files before editing.
  • Make the smallest correct production-quality change.
  • Preserve unrelated user or agent changes in the worktree.
  • Run the smallest meaningful verification command after changes.
  • Report changed files, verification commands, and any unresolved risk back to the parent session.

If the delegated task is unclear, ask one concise clarifying question instead of guessing.

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. yesterday First seen · 21 lines · 25 tokens per session scan A 02512a0bbc58

Subscribe to this mod's changes

Coder is an agent published in the GitHub repository luabagg/agent-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 189 once invoked, about $0.0001 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.