agentmods.dev

conforme adapter-consistency.instructions.md

Project instructions for Conforme, a tool that synchronizes AI coding configuration between products such as Claude Code, Cursor, and other coding tools. They define consistency rules for adapters, documentation, MCP settings, and tests.

In plain words
What is it for?
Adding or changing provider adapters, generating MCP configuration for different coding tools, updating provider documentation, and testing configuration conversions.
Why use it?
They prevent a configuration change from working for one tool while breaking another. They also require related documentation and round-trip tests to stay aligned.

Instructions file for GitHub Copilot

2 8d ago A scan 418 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 instructions/maxgfr/conforme/adapter-consistency
Clone the repo
git clone --depth 1 https://github.com/maxgfr/conforme

Made for: GitHub Copilot.

Per session 418 This file is loaded in full into every session.
When invoked 418 The same file — it is already loaded in full.
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 $0.00418 $0.00418
Opus 5 $0.00209 $0.00209
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 06f616e1f69a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

conforme adapter-consistency.instructions.md 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.

.github/instructions/adapter-consistency.instructions.md · 17 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 · 17 lines · 418 tokens per session scan A 06f616e1f69a

Subscribe to this mod's changes

conforme adapter-consistency.instructions.md is an instructions file published in the GitHub repository maxgfr/conforme (2 stars, last pushed 8d ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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 agentsagents-mdai-codingclaude-codecliconfig-synccopilot
Related

Other instructions, from other repositories

memorix GEMINI.md

Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.

AVIDS2/memorix · 846 tokens

Ctxo CLAUDE.md

Instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).

alperhankendi/Ctxo · 5,885 tokens

anchor copilot-instructions.md

Instructions for peva3/anchor, covering github copilot instructions, required reading, critical rules, prohibited actions and project structure.

peva3/anchor · 683 tokens

open-forge AGENTS.md

Instructions for zhangqi444/open-forge, covering agents.md, what this project is, working on this repo — the rules, build / test / lint and versioning.

zhangqi444/open-forge · 1,700 tokens

Overture CLAUDE.md

Instructions for SixHq/Overture, covering claude.md, project overview, monorepo structure, build & development commands and install dependencies (from root).

SixHq/Overture · 1,450 tokens

ai-protocol AGENTS.md

Instructions for dnlbox/ai-protocol, covering agents.md, instruction format, instruction discovery, project truth and approved objectives.

dnlbox/ai-protocol · 1,370 tokens