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.
npx agentmods add agents/noah-hrbth/agent-tool-sync/adapter-reviewergit clone --depth 1 https://github.com/noah-hrbth/agent-tool-syncWrote 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.
[](https://agentmods.dev/agents/noah-hrbth/agent-tool-sync/adapter-reviewer)<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>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 5.1 | $0.00050 | $0.01211 |
| Opus 5 | $0.00025 | $0.00606 |
| Sonnet 5 | $0.00010 | $0.00242 |
| Haiku 4.5 | $0.00005 | $0.00121 |
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.
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
- The
ToolMetaliteral setsKeyandName, and lists all 4 concepts (Conceptsmap) and both scopes (Scopesmap) explicitly — even unsupported ones, so the support matrix is visible in one literal. Detectis adetectGlobalDir/detectConfigDirclosure (or a customDetectFuncfor irregular probes) — not rawos.Statinlined in the literal.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-emptyReason.Aliasescarries a concept only when the displayed filename differs from the canonical name (e.g. ClaudeConceptRules: "CLAUDE.md").ConceptInfostrings are accurate and specific (no generic "syncs to ~/.tool/" filler).
Render correctness
render<Tool>returnsFileWriteentries with scope-relative paths — no leading/, noos.UserHomeDir()calls, nofilepath.Abs. Paths are joined withfilepath.Joinand built from thepaths.goanchor constants, not re-typed literals.- 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 onruntime.GOOSor env vars. - Frontmatter is built via
buildMDFrontmatter(frontmatter.go) orbuildTOML. No hand-rolled---\n...---strings. No conditional inclusion of zero-value fields — those builders already skip zeros. - Concepts the tool doesn't support (per
Meta.Concepts) are not emitted. Deprecated concepts (Compatibility.Deprecated == true) are also not emitted. - 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 viabuildRootMemoryContent.
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 · 67 lines · 50 tokens per session scan A 98e4d05d0d77
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.