modify-feature

A workflow for extending an existing product feature, such as adding database columns, actions, or API endpoints, without creating a new feature folder.

In plain words
What is it for?
Use it when adding fields to an existing table, changing its behavior, or adding an endpoint, task, or action to an existing feature.
Why use it?
It prevents changes to an existing feature from being treated like a brand-new one. It also keeps database changes, generated code, routes, and tests in the required order.

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/hackbyrd/orbital-express/modify-feature
Any agent
npx skills add Hackbyrd/orbital-express --skill modify-feature
Clone the repo
git clone --depth 1 https://github.com/Hackbyrd/orbital-express

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 931 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 $0.00070 $0.00931
Opus 5 $0.00035 $0.00465
Sonnet 5 $0.00014 $0.00186
Haiku 4.5 $0.00007 $0.00093

Measured 2d ago against content hash 81f8847fe3f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

modify-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/skills/modify-feature/SKILL.md · 26 lines

How it starts

The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Modify an existing feature (Path B — no new folder)

For adding columns and/or methods to a feature that already exists. This is the SAME process as create-feature — the same steps in the same order. It differs in exactly two places: (1) scaffold — you skip the one-time whole-folder yarn gen <Feature> (the folder exists), but you still scaffold every new action/task/mailer (yarn gen <Feature> -a/-t/-m) — modifying is NOT "no scaffolding"; (2) migration — use yarn migration to ALTER (add columns), not yarn model to create a table. Everything else is identical. Composes with create-feature — one product feature can create new table(s) AND modify existing one(s); plan all schema changes together, then run create-feature per new table and this skill per existing table touched. Full order: schema → scaffold (new pieces) → model → migration → routes → controller → actions/tasks → helpers/services → test → run. Full lifecycle: docs/workflow.md.

0. Plan first

  • Decide the new columns (types, defaults, FKs, indexes), actions/tasks, and wiring. Add columns to database/schema.sql, present the plan, and get sign-off before scaffolding or edits. This applies to every modification.
  • Confirm the existing folder has complete standard structure. Preview yarn repair <Feature> --dry-run, review it, then run yarn repair <Feature> before feature edits. Repair never overwrites existing files.

Steps (do only the parts your change needs) — order: schema → model+migration → routes/controller → actions/tasks → run

  1. Model + migration first (if adding columns):
    • Model: add the new field definitions to app/<Feature>/model.js (and indexes/associate if the change adds FKs/indexes). Mirror exactly what you put in schema.sql.
    • Migration — ALTER, not create: make an add-columns migration (see add-migration): yarn migration → rename to <ts>-add-cols-<colA>-and-<colB>-to-<TablePlural>-tbl.js. addColumn/addIndex/addConstraint, transaction-wrapped, named indexes matching the model. Never drop or rename in place (rollback safety) — add new, backfill (you can run SQL right in the migration), remove the old one much later.
  2. Routes + controller — for any new endpoints (feature routes.js + controller method).
  3. New actions and/or tasksyarn gen <Feature> -a V1<Action> / -t V1<Action>Task. Never hand-create when scaffolding exists. Then write the body (see add-action/add-query-action/add-task), register task processors in worker.js, add supporting constants/errors/i18n/mailers/helpers/services, and complete every generated test. Root routes, models, workers, and errors auto-discover features.
  4. Run checks/tests: yarn conventions:check, focused tests, then yarn test. Finish with the mandatory review-conventions self-audit.

Read the full file on GitHub · 26 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 · 26 lines · 70 tokens per session scan A 81f8847fe3f5

Subscribe to this mod's changes

modify-feature is a skill published in the GitHub repository Hackbyrd/orbital-express (14 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 931 once invoked, about $0.0003 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 2026-08-30.

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