incremental-implementation

incremental-implementation is a skill for Claude Code, Codex from swimmwatch/cloakbrowser-mcp. It costs 97 tokens per session (507 once invoked), scanned A, original, MIT.

A controlled implementation workflow for completing one explicitly approved task packet at a time. A task packet is a written unit of development work with defined requirements, files, risks, and checks.

In plain words
What is it for?
Implementing TypeScript, MCP bridge, command-line, HTTP, packaging, Docker, CI, security, or documentation tasks planned under project specifications, then verifying and recording the result.
Why use it?
It limits each change to a clearly agreed piece of work and requires checking the previous work before starting the next piece. This helps prevent unfinished or unrelated changes from being mixed together.

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/swimmwatch/cloakbrowser-mcp/incremental-implementation
Any agent
npx skills add swimmwatch/cloakbrowser-mcp --skill incremental-implementation
Clone the repo
git clone --depth 1 https://github.com/swimmwatch/cloakbrowser-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for incremental-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/incremental-implementation.svg)](https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/incremental-implementation)
Your own site
<a href="https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/incremental-implementation"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/incremental-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 507 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 $0.00097 $0.00507
Opus 5 $0.00048 $0.00253
Sonnet 5 $0.00019 $0.00101
Haiku 4.5 $0.00010 $0.00051

Measured 5d ago against content hash b42a202b92d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

incremental-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 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.

.agents/skills/incremental-implementation/SKILL.md · 38 lines

What it actually says

Incremental Implementation

  1. Read AGENTS.md, .agents/references/task-packets.md, the active docs/specs/<slug>/tasks/todo.md item, its linked packet, and handoff.md only when continuing.
  2. Do not read the full specification, full plan, or unrelated packets unless the packet identifies a material conflict. Return incomplete or contract-changing packets to /plan or /spec.
  3. Before a newly authorized packet, inspect the worktree for the completed previous packet. If its changes remain uncommitted:
    • verify completion and match them to the handoff;
    • use Prompt MCP to obtain explicit commit authorization if not already recorded;
    • after authorization, scan Conventional Commits 1.0.0 and commit only the previous packet's changes;
    • preserve and exclude unrelated worktree changes;
    • do not start the new packet until this gate is resolved.
  4. Confirm outcome, non-goals, owned requirement IDs, public contracts, expected files, risks, rollback, manual gates, and verification before editing.
  5. Implement only that packet. Preserve strict TypeScript/ESM, unchanged upstream tools, the two local tools, stdout safety, process cleanup, HTTP session isolation, and unrelated user changes.
  6. Run the packet's focused commands and applicable npm run check. Stop before any external-state MANUAL GATE.
  7. Update the packet checklist, todo.md, and handoff.md with files, checks, blockers, unrelated worktree state, and the next packet.
  8. Present the evidence and stop for review. Leave the current packet uncommitted unless the user explicitly authorized an earlier commit.

Never infer authorization from approval of the specification or plan. Commit, push, PR, merge, tag, publish, release, and the next packet are separate gates.

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. 5d ago First seen · 38 lines · 97 tokens per session scan A b42a202b92d4

Subscribe to this mod's changes

incremental-implementation is a skill published in the GitHub repository swimmwatch/cloakbrowser-mcp (55 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 507 once invoked, about $0.0005 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

browser-search

Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.

Johell1NS/browser-search · 36 tokens

chrome-orchestrator

Teach agents how to orchestrate Arthur and Gloria headless Chrome environments dynamically via the Python SDK and CLI.

sh7vansh/chrome-orchestrator · 26 tokens

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens

opencli-autofix

Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.

jackwener/OpenCLI · 61 tokens