feature-implementation

A compatibility procedure for implementing one focused software feature. It emphasizes a thin vertical slice, meaning the smallest working path from user need to functioning result.

In plain words
What is it for?
It helps confirm scope, trace the production path, implement the smallest usable change, run an early real-world check, and handle only failures that block the result.
Why use it?
It keeps feature work tied to an accepted outcome and avoids building broad infrastructure before the first useful path works.

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/megamen32/lasthumancommit/feature-implementation
Any agent
npx skills add megamen32/LastHumanCommit --skill feature-implementation
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 264 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 $0.00040 $0.00264
Opus 5 $0.00020 $0.00132
Sonnet 5 $0.00008 $0.00053
Haiku 4.5 $0.00004 $0.00026

Measured yesterday against content hash 697c0ab0657b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-implementation 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.

plugins/last-human-commit/skills/feature-implementation/SKILL.md · 32 lines

What it actually says

Feature Implementation

For new assignments, load worker-code; it supersedes this compact alias with reusable research-map and rg guidance.

Use when one coherent vertical feature contribution is cheaper to delegate than to execute directly.

Procedure

  1. Confirm the accepted outcome, actual production path, allowed scope, and shortest acceptance check.
  2. Reuse the existing mechanism and implement the thinnest usable vertical.
  3. Run the real canary early, then fix only the first claim-blocking failure.
  4. Add only proportional direct-regression evidence.
  5. At each 20-minute checkpoint report business delta and remain available for continuation or redirection.
  6. Ask Lead at every context-dependent decision boundary with evidence, recommendation/default, parallel-safe work, and the exact blocked action; continue safe work through a non-blocking parent transport when available.

Do not

  • Do not implement horizontal completeness before the first usable path.
  • Do not redesign architecture or add unrelated hardening.
  • Do not treat local compilation as final product proof.
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 · 32 lines · 40 tokens per session scan A 697c0ab0657b

Subscribe to this mod's changes

feature-implementation is a skill published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 264 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.

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