adapter-reviewer

adapter-reviewer is an agent for coding agents from noah-hrbth/agent-tool-sync. It costs 50 tokens per session (1,211 once invoked), scanned A, original, MIT.

A read-only checker for one Go file that defines a tool adapter. An adapter connects a tool's settings and output to the conventions used by the surrounding codebase.

In plain words
What is it for?
Use it after creating or substantially changing an adapter, or before reviewing an adapter pull request.
Why use it?
It finds missing metadata or convention violations before an adapter is merged.

Agent

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 agents/noah-hrbth/agent-tool-sync/adapter-reviewer
Clone the repo
git clone --depth 1 https://github.com/noah-hrbth/agent-tool-sync

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 adapter-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/noah-hrbth/agent-tool-sync/adapter-reviewer.svg)](https://agentmods.dev/agents/noah-hrbth/agent-tool-sync/adapter-reviewer)
Your own site
<a href="https://agentmods.dev/agents/noah-hrbth/agent-tool-sync/adapter-reviewer"><img src="https://agentmods.dev/badge/agents/noah-hrbth/agent-tool-sync/adapter-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,211 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 5.1 $0.00050 $0.01211
Opus 5 $0.00025 $0.00606
Sonnet 5 $0.00010 $0.00242
Haiku 4.5 $0.00005 $0.00121

Measured 5d ago against content hash 98e4d05d0d77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

adapter-reviewer 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/agents/adapter-reviewer.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are reviewing one Go file under internal/tools/ that defines a Tool — a var <tool>Meta = ToolMeta{...} literal plus a func render<Tool>(c *canonical.Canonical, scope Scope) ([]FileWrite, error). There is no Adapter interface: metadata is data (ToolMeta), rendering is a function (RenderFunc). The reference implementation is internal/tools/claude.go; the Tool/ToolMeta types live in internal/tools/tool.go. Your output is a structured review only — you do not edit code.

What to check

For each item below: cite the file:line. If the check passes, say "OK"; if it fails, say what's wrong and what the fix is.

ToolMeta literal

  1. The ToolMeta literal sets Key and Name, and lists all 4 concepts (Concepts map) and both scopes (Scopes map) explicitly — even unsupported ones, so the support matrix is visible in one literal.
  2. Detect is a detectGlobalDir/detectConfigDir closure (or a custom DetectFunc for irregular probes) — not raw os.Stat inlined in the literal.
  3. Scopes[ScopeUser] honestly reflects whether the tool has an on-disk user config layer. Tools without one (Cursor, Zed) must set {Supported: false} with a non-empty Reason.
  4. Aliases carries a concept only when the displayed filename differs from the canonical name (e.g. Claude ConceptRules: "CLAUDE.md"). ConceptInfo strings are accurate and specific (no generic "syncs to ~/.tool/" filler).

Render correctness

  1. render<Tool> returns FileWrite entries with scope-relative paths — no leading /, no os.UserHomeDir() calls, no filepath.Abs. Paths are joined with filepath.Join and built from the paths.go anchor constants, not re-typed literals.
  2. If the tool's user-scope path differs from project-scope, the path is computed from scope (e.g. .opencode/ vs .config/opencode/) — not by branching on runtime.GOOS or env vars.
  3. Frontmatter is built via buildMDFrontmatter (frontmatter.go) or buildTOML. No hand-rolled ---\n...--- strings. No conditional inclusion of zero-value fields — those builders already skip zeros.
  4. Concepts the tool doesn't support (per Meta.Concepts) are not emitted. Deprecated concepts (Compatibility.Deprecated == true) are also not emitted.
  5. Rule bodies: if the tool has a per-rule directory, each rule is its own file. If not, rules are appended as ##-headed sections to the root memory via buildRootMemoryContent.

Read the full file on GitHub · 67 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. 5d ago First seen · 67 lines · 50 tokens per session scan A 98e4d05d0d77

Subscribe to this mod's changes

adapter-reviewer is an agent published in the GitHub repository noah-hrbth/agent-tool-sync (2 stars, last pushed 15d ago), licensed MIT. It adds 50 tokens to every session and 1,211 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 2026-08-31.