agentmods.dev

conforme: Instructions file for GitHub Copilot

.github/instructions/adapter-consistency.instructions.md

conforme adapter-consistency.instructions.md is an instructions file for GitHub Copilot from maxgfr/conforme. It costs 1,556 tokens per session, scanned A, original, MIT.

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

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

This is maxgfr/conforme's own configuration. It tells GitHub Copilot how to work on conforme itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything conforme configures →

not rated 5repo changed 14d ago A scan 1,556 tokens original MIT
View source ↗ maxgfr/conforme
Reuse

Borrowing it

Nothing to install: this file belongs to maxgfr/conforme. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/maxgfr/conforme/main/.github/instructions/adapter-consistency.instructions.md
Clone the repo
git clone --depth 1 https://github.com/maxgfr/conforme

Made for: GitHub Copilot.

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 conforme adapter-consistency.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/maxgfr/conforme/adapter-consistency/github.svg)](https://agentmods.dev/instructions/maxgfr/conforme/adapter-consistency)
Your own site
<a href="https://agentmods.dev/instructions/maxgfr/conforme/adapter-consistency"><img src="https://agentmods.dev/badge/instructions/maxgfr/conforme/adapter-consistency/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for conforme adapter-consistency.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/maxgfr/conforme/adapter-consistency"><img src="https://agentmods.dev/badge/instructions/maxgfr/conforme/adapter-consistency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,556 This file is loaded in full into every session.
When invoked 1,556 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01556 $0.01556
Opus 5.5 $0.00622 $0.00622
Sonnet 5.5 $0.00311 $0.00311
Haiku 4.5 $0.00156 $0.00156

Measured 14d ago against content hash 57d5a04fa4f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 14d 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 · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

  • Every adapter change MUST be reflected in its docs/providers/<tool>.md
  • Every MCP format change MUST update the tool's ServerShape (or the Codex / Vibe TOML merge) AND its unit test
  • MCP keys and shapes per tool are the "MCP key mapping per tool" table in CLAUDE.md: update it with any MCP change
  • 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, back each fact with the vendor page, changelog or source it comes from, and carry a Last verified online line (date, upstream version) that verify-providers updates
  • Test round-trips: read() output fed into generate() should produce identical files
  • A JSON MCP entry shape is a ServerShape in src/mcp.rs (type values, URL key, env on remote, env-var syntax, layout, on/off toggle) with its build, owned_keys and read; add or change a tool there rather than writing another builder, owned-key list or reader
  • Devin (formerly Windsurf): write .devin/ only; .windsurf/ is read as a legacy location (Devin loads both) and conforme's old copies there are cleaned. Project MCP is .devin/mcp_config.json; never generate .windsurf/mcp.json
  • Never add a user-authored directory (e.g. .github/prompts/) to managed_directories(): orphan cleanup deletes every file there that carries the directory's suffix and that conforme did not generate
  • Give each ManagedDir the exact suffix conforme writes there (ManagedDir::files(dir, ".agent.md")), and use ManagedDir::subdirs for skills directories, so files the tool accepts but conforme never writes (Kiro .json agents, dsh flat skills) survive a sync
  • An adapter must generate no files for an empty config and never a blank file (guarded by test_no_adapter_writes_blank_files)
  • When an upstream tool is retired (as Amazon Q was), delete its adapter outright rather than keeping it behind a deprecation flag; the removal checklist is the mirror of the "adding a new adapter" one above
  • Every MCP file is merged, never owned: any adapter that merges into a user-owned settings file (.mcp.json, .cursor/mcp.json, .kiro/settings/mcp.json, .devin/mcp_config.json, opencode.json, .zed/settings.json, .gemini/settings.json, kilo.jsonc, .vscode/mcp.json, .github/mcp.json, .roo/mcp.json, .codex/config.toml, .vibe/config.toml, .agents/mcp_config.json) MUST implement is_shared_file() so remove and migrate never delete it wholesale, and its gitignore patterns must not match it
  • Merge JSON settings through json_settings::server_settings_file (or load/merge_server_entries/render_with_removals), never serde_json::from_str(..).unwrap_or_default(): those files are JSONC, a parse failure must refuse the write instead of replacing the user's file, and a source with no server leaves the file untouched
  • A setting a tool will not load as written (a ${VAR} it cannot resolve, a reserved name, a file it refuses) is reported by AiToolAdapter::warnings, which sync and migrate print
  • 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
  • Skills and agents always carry a description (description_or_name): Codex, Copilot, Gemini, OpenCode and Zoo Code skip one without it
  • A skill is its whole folder: every reader fills NormalizedSkill::files (read_bundled_files) and skills::generate_skills writes them beside SKILL.md (bundled_outputs), each tool's layout being a SkillShape; each generated skill folder holds the .conforme marker (SKILL_MARKER), and a folder that already held a hand-written SKILL.md without it is never adopted; its skills directory is a ManagedDir::subdirs, so the copies are kept in step (stale_bundled_files, and a marked folder whose skill left the source is deleted by stale_skill_folder_files, never in a directory the source reads) and verify-providers' skills_conformity.py passes
  • Tools with their own tool vocabulary (Claude Code, Gemini CLI, Kiro, Mistral Vibe) get translated tools lists (TOOL_EQUIVALENTS, MCP names respelled), never names copied verbatim from another host; a model another tool cannot use is left out (claude_model, gemini_model, opencode_model, kiro_model, copilot_model, cursor_model)
  • Skill and agent names go through sanitize_name (kebab-case ASCII, at most 64 characters), rule file names through rule_file_name, and MCP strings through EnvRefStyle so ${VAR} becomes each tool's own reference syntax
  • A tool that reads AGENTS.md itself in a project returns true from reads_agents_md(project_root) (always for Codex, OpenCode, DeepSeek, Mistral Vibe, Kilo Code; Claude Code without CLAUDE.md; Gemini CLI when context.fileName names it) and reads it with markdown::read_native_agents_md; renaming a tool id adds it to project_config::RENAMED_IDS
  • A file or directory read() loads outside the tool's managed directories (a native or fallback AGENTS.md / CLAUDE.md, Gemini's context files, Devin's global_rules.md / .windsurfrules, Zoo's .roorules, DeepSeek's and Vibe's .agents/skills fallback, Kilo's rule directories) MUST be returned by source_files(project_root) when it exists and is used, so that with the tool as source no target writes it, remove/migrate never delete it and gitignore install never ignores it; a new read location also goes into watch::source_locations
  • A server entry conforme cannot express (no command — a string, OpenCode's array or Zed's legacy {path, args, env} — no URL, or Claude type: "sdk") is skipped on read and kept on write (json_settings::is_expressible_server); a disabled one only in a tool whose own toggle it is (ServerShape.toggle)

Read the full file on GitHub · 30 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. 14d ago Changed · +103 tokens per session 57d5a04fa4f1
  2. 16d ago Changed · -2 lines · -172 tokens per session 8d031b0616d5
  3. 18d ago Changed · +4 lines · +541 tokens per session 26bb169a1285
  4. 25d ago Changed · +3 lines · +293 tokens per session 61d3e7da0796
  5. 27d ago Changed · +4 lines · +197 tokens per session b40e7a22e8ea
  6. 1mo ago Changed · +4 lines · +176 tokens per session f9bbe1a961da
  7. 1mo 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 (5 stars, last pushed 6d ago), licensed MIT. It adds 1,556 tokens to every session, about $0.0062 per session on Opus 5.5. 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 agentsClaude Codeagents-mdai-codingcliconfig-synccopilot
Related

Other instructions, from other repositories

whichrules copilot-instructions.md

Instructions for z35068037/whichrules, a project described as: See exactly which instructions your AI coding agent receives - and where they conflict.

z35068037/whichrules · 21 tokens

ai-agent-rules-generator ui-design.instructions.md

Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.

savedpixel/ai-agent-rules-generator · 701 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens