code-implementer

A coding workflow for implementing software from an architecture or plan document, producing production code and tests. It follows TDD: write a failing test, make it pass with minimal code, then clean up.

In plain words
What is it for?
Use it to build features, add endpoints or components, and make the smallest supporting changes to migrations, configuration, or type definitions.
Why use it?
It keeps implementation tied to an agreed design, limits unrelated changes, and checks uncertain behavior by running tests instead of guessing.

Skill for Claude CodeCodex

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 skills/spumer/i-m-senior-developer/code-implementer
Any agent
npx skills add spumer/i-m-senior-developer --skill code-implementer
Clone the repo
git clone --depth 1 https://github.com/spumer/i-m-senior-developer

Made for: Claude Code, Codex.

Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,566 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 $0.00150 $0.04566
Opus 5 $0.00075 $0.02283
Sonnet 5 $0.00030 $0.00913
Haiku 4.5 $0.00015 $0.00457

Measured 2d ago against content hash c414b763d3e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-implementer 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.

plugins/sdlc/skills/code-implementer/SKILL.md · 422 lines

How it starts

The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code-Implementer — TDD-first implementation

Implements code per a design document (ARCH, PLAN, or README with explicit scope). Output: production code + tests + minimal supporting changes (migrations, configs, type stubs). Never designs systems; never reviews others' code.

Principles

  1. TDD-first. Activate tdd-master:tdd-master BEFORE writing any production code. RED (failing test) → GREEN (minimum code to pass) → REFACTOR (cleanup, suite stays green). This order is non-negotiable.

  2. Minimal changes (FPF A.11). Modify the smallest set of lines that satisfies the test. Do not refactor adjacent code in passing. If adjacent code blocks the implementation, surface that as an ## Open question in the next architecture iteration — do not silently rewrite.

  3. Fail-fast. Validate inputs at function boundary. Raise typed exceptions (Python) / throw early (TypeScript). Do not return None/null to signal error when a typed exception is the better tool.

  4. Evidence over assumption (FPF A.10). Before claiming "this works the same way" — write a test, run it, look at the result. Prediction → Run → Compare. Do not assert behavior from reading code alone.

  5. Don't change contract without discussion. Signature, return type, and behavior for the calling code = breaking change. See Code-Change Discipline rule 6 (functional-clarity:functional-clarityreferences/02-code-change-discipline.md). Surface the intention before committing to the change.

  6. Apply Functional Clarity. If functional-clarity:functional-clarity is installed, activate it for the full 22-principle methodology. Key: Error Hiding prevention, fail-fast taxonomy, bounded context invariants.

  7. A green suite is necessary, not sufficient (FPF A.10, widened). Passing unit/integration tests are one evidence source — not proof the change works in the running system. Runtime behavior, a write actually landing, and a value's real wire shape are separate evidence the suite does not provide. Establish them before "done" — see Verification beyond the suite below.

Read the full file on GitHub · 422 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 422 lines · 150 tokens per session scan A c414b763d3e2

Subscribe to this mod's changes

code-implementer is a skill published in the GitHub repository spumer/i-m-senior-developer (11 stars, last pushed 10d ago), licensed MIT. It adds 150 tokens to every session and 4,566 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens