agentmods.dev

adapter-consistency

A set of project rules for keeping tool adapters, documentation, generated MCP configuration, and tests consistent.

In plain words
What is it for?
For adding or changing adapters, updating MCP configuration formats, preserving user settings, and checking that file generation round-trips correctly.
Why use it?
It reduces the chance that a change works in one place but leaves documentation, generated files, tests, or provider-specific settings outdated.

Cursor rule for Cursor

2 7d ago A scan 0 tokens original MIT
View the source file maxgfr/conforme
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 rules/maxgfr/conforme/adapter-consistency
Clone the repo
git clone --depth 1 https://github.com/maxgfr/conforme

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 429 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 $0.00000 $0.00429
Opus 5 $0.00000 $0.00215
Sonnet 5 $0.00000 $0.00086
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash a348725deca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adapter-consistency 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 2d 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.

.cursor/rules/adapter-consistency.mdc · 19 lines

What it actually says

  • Every adapter change MUST be reflected in its docs/providers/<tool>.md
  • Every MCP format change MUST update the corresponding generate_*_mcp_json function AND its unit test
  • When adding a new adapter, update ALL of: README.md tables, src/help_ai.rs, src/cli.rs tool count, CLAUDE.md architecture section
  • Provider docs must list all official documentation URLs for the tool
  • Test round-trips: read() output fed into generate() should produce identical files
  • MCP JSON keys per tool: Claude/Windsurf/Kiro/RooCode/AmazonQ/Gemini/Cursor/Continue.dev = mcpServers, Copilot = servers, OpenCode = mcp (inside opencode.json), Zed = context_servers, Amp = amp.mcpServers
  • OpenCode MCP specifics: command is a single array [cmd, ...args], env key is environment (not env), servers live inside opencode.json at project root (conforme merges — never clobber user-authored keys)
  • Windsurf MCP specifics: no type field; HTTP transport uses serverUrl (not url)
  • Amp MCP specifics: dotted amp.mcpServers key, no type field, merged into .amp/settings.json (never clobber user settings)
  • Cursor subagents: .md extension (not .mdc); no tools frontmatter field — tool access is inherited from the parent agent
  • Copilot skills: .github/skills/<name>/SKILL.md (NOT .github/prompts/*.prompt.md — prompt files are a separate VS Code feature)
  • Any adapter whose generate() writes skills, agents, or MCP MUST read them back in read(), or --from <tool> silently drops them
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. 2d ago First seen · 19 lines · 0 tokens per session scan A a348725deca3

Subscribe to this mod's changes

adapter-consistency is a cursor rule published in the GitHub repository maxgfr/conforme (2 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 429 tokens. 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.

TestingWriting and docsagents-mdai-codingclaude-codecliconfig-synccopilot
Related

Other cursor rules, from other repositories

cursor-project-rule

Project Spine operating contract for "Ledger API".

PetriLahdelma/project-spine · 211 tokens

project-spine-apps-web

Project Spine scoped guidance for "apps/web".

PetriLahdelma/project-spine · 0 tokens

project-spine-packages-ui

Project Spine scoped guidance for "packages/ui".

PetriLahdelma/project-spine · 0 tokens

project

Core project context for ai-context-kit.

ofershap/ai-context-kit · 648 tokens

checklist

Before making ANY changes or implementing ANY new features.

Kabi10/cursor-rules · 432 tokens

nextjs-patterns

// ✅ Correct: Default to Server Components export default async function Page({ params }) { const data = await getData(); return ; }.

Kabi10/cursor-rules · 456 tokens