A development helper for adding support for a new tool in agentsync, a program that translates tool configuration between coding agents. It creates the required Go code, registrations, reverse mapping, tests, metadata, and documentation updates.

Use it when implementing a tool listed in TODO.md. It helps research the tool's configuration layout, define its metadata and rendering behavior, register it, test round trips, and update generated compatibility information.

It removes the need to make all of these connected changes by hand and helps keep forward conversion, reverse conversion, tests, and compatibility records aligned.

add-adapter — Skill for Claude Code and Codex by noah-hrbth: A development helper for adding support for a new…

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/noah-hrbth/agent-tool-sync/add-adapter

Any agent

npx skills add noah-hrbth/agent-tool-sync --skill add-adapter

Clone the repo

git clone --depth 1 https://github.com/noah-hrbth/agent-tool-sync

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/noah-hrbth/agent-tool-sync/add-adapter.svg)](https://agentmods.dev/skills/noah-hrbth/agent-tool-sync/add-adapter)

Your own site

<a href="https://agentmods.dev/skills/noah-hrbth/agent-tool-sync/add-adapter"><img src="https://agentmods.dev/badge/skills/noah-hrbth/agent-tool-sync/add-adapter.svg" alt="Measured on agentmods" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,685 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	$0.00103	$0.01685
Opus 5	$0.00051	$0.00843
Sonnet 5	$0.00021	$0.00337
Haiku 4.5	$0.00010	$0.00169

Measured 5d ago against content hash 3dcfd175b705, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-adapter 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.

.agentsync/skills/add-adapter/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a New Tool Adapter

Goal: define a new Tool end-to-end. A Tool is a pure value — Tool{ Meta ToolMeta; Render RenderFunc }; there is no Adapter interface. Mirror the conventions in internal/tools/claude.go (the reference implementation); the types live in internal/tools/tool.go.

0. Research the target tool — do not skip

Find primary-source docs for the tool's config layout. Confirm:

Config dir: ~/.<tool>/ or ~/.config/<tool>/? (detectGlobalDir vs detectConfigDir)
Project layout: .<tool>/... at workspace root? Anything special?
Root memory file (name + format): does it live at workspace root or under the tool dir?
Per-rule files supported? Subdir layout? File extension (.md, .mdc, .toml)?
Skills, agents, slash commands: which concepts exist? Frontmatter schema for each?
User scope: is there an on-disk user config layer? If not, set Scopes[ScopeUser] = {Supported: false, Reason: "..."}.
Deprecations: any concept the tool flags as legacy? (set Compatibility.Deprecated = true with a Replacement).

Cite the source URL in the tool file as a one-line comment above the ToolMeta literal. If docs are ambiguous, prefer WebFetch over guessing.

1. Create `internal/tools/<tool>.go`

Use claude.go as the template. The file holds two things, co-located:

var <tool>Meta = ToolMeta{...} — the data descriptor:

Key — stable lowercase id (e.g. "windsurf"). Name — display name in Title Case (e.g. "Windsurf").
Detect — detectGlobalDir("<tool>") or detectConfigDir("<tool>") (or a custom DetectFunc closure for irregular probes).
Concepts — list all 4 concepts explicitly: {Supported: true} per natively-supported concept; {Supported: false, Reason: "..."} for unsupported; mark deprecated concepts with Deprecated: true, Replacement: "<successor>".
Scopes — list both scopes explicitly; {Supported: false, Reason: "..."} for scopes with no on-disk layer (see cursor.go, zed.go user scope).
Aliases — only for concepts whose displayed filename differs from the canonical name (e.g. Claude ConceptRules: "CLAUDE.md"). Omit otherwise.
ConceptInfo — a specific per-concept help string for the TUI Tools screen (real paths, not generic filler).

Read the full file on GitHub · 98 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 · 98 lines · 103 tokens per session scan A 3dcfd175b705

Subscribe to this mod's changes

add-adapter is a skill published in the GitHub repository noah-hrbth/agent-tool-sync (2 stars, last pushed 15d ago), licensed MIT. It adds 103 tokens to every session and 1,685 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 2026-08-31.

Building agents

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