implement-feature

A guided workflow for implementing software features through research, planning, test-driven development, and documentation. Test-driven development means writing a failing test first, then coding until the test passes.

In plain words
What is it for?
Implementing a feature from a description, GitHub issue, or gap-analysis item while reviewing project conventions, affected code, tests, and documentation.
Why use it?
It gives a feature change a repeatable path from understanding the existing code to verifying and documenting the result.

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/arc-mcp/arc-1/implement-feature
Clone the repo
git clone --depth 1 https://github.com/arc-mcp/arc-1

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,556 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 $0.00000 $0.02556
Opus 5 $0.00000 $0.01278
Sonnet 5 $0.00000 $0.00511
Haiku 4.5 $0.00000 $0.00256

Measured 2d ago against content hash 6a93fa4de1dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

implement-feature 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 2d 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.

.claude/commands/implement-feature.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Implement Feature

Quality-first implementation workflow for ARC-1 features. Guides you through research, planning, test-driven development, and documentation updates.

Input

The user provides a feature description — either a reference to a gap analysis item (e.g., from docs/compare/08-dassian-adt-feature-gap.md), a GitHub issue, or a free-form description.

SAP auth guidance:

  • When touching auth (Layer A or Layer B), read docs_page/enterprise-auth.md#coexistence-matrix first. The validateConfig fail-fast rules in src/server/config.ts are the authoritative source — extend them if adding a new combination.

Ask the user for:

  • Feature description (required) — what to implement
  • Scope (optional) — small/medium/large, helps calibrate effort

If only a description is given, infer scope from the description and proceed.


Phase 1: Research & Understand

Before writing any code, understand the full picture.

1a. Read project guidelines

Read CLAUDE.md to refresh on project conventions, code patterns, and key file mappings.

1b. Understand existing code in the affected area

Based on the feature description, identify and read all relevant source files. Use the "Key Files for Common Tasks" table in CLAUDE.md as a starting point:

Task Files
Add new read operation src/adt/client.ts, src/handlers/read.ts, src/handlers/tools.ts
Add new tool type src/handlers/tools.ts, src/handlers/schemas.ts, src/handlers/dispatch.ts
Add safety check src/adt/safety.ts
Add XML parser rule src/adt/xml-parser.ts
Add error handling src/adt/errors.ts, src/handlers/dispatch.ts
Add transport feature src/adt/transport.ts, src/handlers/transport.ts
Add DDIC domain/data element write src/adt/ddic-xml.ts, src/adt/crud.ts, src/handlers/write.ts, src/handlers/schemas.ts, src/handlers/tools.ts
Add context feature src/context/compressor.ts, src/context/deps.ts
Add CDS impact analysis context src/adt/cds-impact.ts, src/adt/codeintel.ts (findWhereUsed), src/handlers/context.ts (SAPContext action="impact"), tests/unit/adt/cds-impact.test.ts
Add diagnostic src/adt/diagnostics.ts, src/handlers/diagnose.ts

Read the full file on GitHub · 252 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. 2d ago First seen · 252 lines · 0 tokens per session scan A 6a93fa4de1dc

Subscribe to this mod's changes

implement-feature is a command published in the GitHub repository arc-mcp/arc-1 (174 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,556 tokens. 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.