implement

Implement an issue directly on a new branch, then commit and open a PR once the user approves the diff.

Command for Claude Code

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 commands/kavo-labs/kavo/implement
Clone the repo
git clone --depth 1 https://github.com/kavo-labs/kavo

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,314 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 $0.00021 $0.01314
Opus 5 $0.00010 $0.00657
Sonnet 5 $0.00004 $0.00263
Haiku 4.5 $0.00002 $0.00131

Measured today against content hash 29816e389e4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement 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 today.

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.

.claude/commands/implement.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context

  • Current branch: !git rev-parse --abbrev-ref HEAD
  • Working tree: !git status --short
  • Recent commits: !git log --oneline -5

Your task

Arguments: $ARGUMENTS — the first token is the issue number; anything after it is extra instructions or corrections to fold in during implementation.

  1. Preflight. If no issue number was given, stop and ask for one. If there is no GitHub remote, stop and say so.

  2. Read the issue in full: gh issue view <n> --json title,body,labels,comments. Restate its goal and acceptance criteria to yourself so the implementation is judged against them, not against a guess. If the issue is too vague to implement — missing acceptance criteria, an ambiguous design choice with no default the codebase implies — stop and ask rather than guessing; do not silently narrow the scope.

  3. Locate the seam before writing code. Kavo is built out of swappable seams (packages/core/src/engine/kavo-engine.ts's Template Method: operation resolution → config resolution → DTO resolution → deserialization → query resolution → handler execution → response mapping → serialization). Most changes are "add or modify a seam", not "add a branch" — find the existing seam before proposing a new mechanism. Check the invariants and ADRs your change touches (registry-driven operations, ADR-0006; decoration-time routes, ADR-0012; the explicit named barrel, ADR-0010; the composition root freezing after createCrud) and read the governing ADR in docs/internals/adr/ before changing behavior it covers. Follow the naming conventions in CLAUDE.md — they are normative.

  4. Create the branch, in an isolated worktree. Follow the conventions skill to derive <type> from the issue's label. Call EnterWorktree with name: "<issue-number>-<short-slug>" to create a fresh worktree — branched off up-to-date main — and switch the session into it, then rename the branch to match the convention: git branch -m <type>/<issue-number>-<short-slug>. Implementing in a worktree keeps this work off the branch the user's editor has open.

Read the full file on GitHub · 114 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. today First seen · 114 lines · 21 tokens per session scan A 29816e389e4c

Subscribe to this mod's changes

implement is a command published in the GitHub repository kavo-labs/kavo (12 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 1,314 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 2026-09-02.