A workflow for changing existing software features, with checks for affected parts and compatibility. It is intended for changes to behavior that already works, including refactoring and deprecation.

Updating APIs, adding behavior to existing features, changing authentication, refactoring code, deprecating features, and analysing the impact of a proposed change.

Changing working code can affect related features or break compatibility. This workflow helps examine those effects before making the change.

ss-modify — Skill for Claude Code and Codex by MartyBonacci: A workflow for changing existing software features, with checks…

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/martybonacci/specswarm/ss-modify

Any agent

npx skills add MartyBonacci/specswarm --skill ss-modify

Clone the repo

git clone --depth 1 https://github.com/MartyBonacci/specswarm

Made for: Claude Code, Codex.

Or install ss, the plugin that ships this one along with the rest of its 10 skills, 34 commands, 6 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/martybonacci/specswarm/ss-modify.svg)](https://agentmods.dev/skills/martybonacci/specswarm/ss-modify)

Your own site

<a href="https://agentmods.dev/skills/martybonacci/specswarm/ss-modify"><img src="https://agentmods.dev/badge/skills/martybonacci/specswarm/ss-modify.svg" alt="Measured on agentmods" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,197 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.

Model	Per session	Once invoked
Fable 5	$0.00023	$0.01197
Opus 5	$0.00012	$0.00598
Sonnet 5	$0.00005	$0.00239
Haiku 4.5	$0.00002	$0.00120

Measured 5d ago against content hash 8d516ef7d486, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ss-modify 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 5d 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/ss/skills/ss-modify/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SpecSwarm Modify Workflow

Provides natural language access to /ss:modify command.

When to Invoke

Trigger this skill when the user mentions:

Modifying, changing, or updating existing feature behavior
Enhancing or extending working features
Altering how something works (that currently works)
Making features work differently than they do now
Refactoring code for quality improvement (without changing behavior)
Deprecating or sunsetting features

Examples:

"Change authentication from session to JWT"
"Add pagination to the user list API"
"Update search to use full-text search"
"Modify the dashboard to show real-time data"
"Extend the API to support filtering"
"Refactor this module to reduce complexity" → uses --refactor
"Deprecate the v1 API" → uses --deprecate
"What's the impact of changing the user model?" → uses --analyze-only

NOT for this skill:

Fixing bugs (use ss-fix)
Building new features (use ss-build)

Instructions

Skill-Based Routing:

Detect that user mentioned modifying/changing existing functionality
Extract the modification description from their message
Route based on intent clarity:

Clear intent - Execute directly:
- Clear modification requests: "Change authentication from session to JWT", "Add pagination to user list API", "Update search algorithm to use full-text search"
- Clear refactor requests: "Refactor this module to reduce complexity", "Clean up the utils to reduce duplication"
- Clear deprecation requests: "Deprecate the v1 API", "Sunset the legacy auth system"
- Action: Immediately run the appropriate command:
  - Standard modify: /ss:modify "modification description"
  - Refactor: /ss:modify "target" --refactor
  - Deprecate: /ss:modify "target" --deprecate
  - Impact analysis only: /ss:modify "target" --analyze-only
Ambiguous intent - Ask for confirmation:
- Less specific: "Update the authentication", "Make the feature better"
- Action: Use AskUserQuestion tool with two options:
  - Option 1 (label: "Run /ss:modify"): Use SpecSwarm's workflow
  - Option 2 (label: "Process normally"): Handle as regular Claude Code request

Read the full file on GitHub · 142 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.

5d ago First seen · 142 lines · 23 tokens per session scan A 8d516ef7d486

Subscribe to this mod's changes

ss-modify is a skill published in the GitHub repository MartyBonacci/specswarm (65 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,197 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 2026-08-30.

systematic-debugging

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

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens