RepoGrammar: Skill for Claude Code

.agents/skills/mcp-contract-change/SKILL.md

mcp-contract-change is a skill for Claude Code, Codex from SioYooo/RepoGrammar. It costs 28 tokens per session (369 once invoked), scanned A, original, MIT.

A set of instructions for changing the MCP contract: the names, inputs, outputs, data format, and error behavior of tools used by AI agents. MCP, or Model Context Protocol, is a standard way for agents to call external tools.

In plain words
What is it for?
Use it when changing MCP tools, their schemas, serialization, return values, or documented errors in RepoGrammar. It covers specification updates, compatibility checks, tests, documentation, and verification.
Why use it?
It helps prevent changes from breaking existing tool users or mixing transport details into the core application. It also requires the written specification and tests to stay aligned with the code.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is SioYooo/RepoGrammar's own configuration. It tells Claude Code and Codex how to work on RepoGrammar 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 RepoGrammar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SioYooo/RepoGrammar. 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/SioYooo/RepoGrammar/main/.agents/skills/mcp-contract-change/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SioYooo/RepoGrammar

Made for: Claude Code, Codex.

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 mcp-contract-change

README.md
[![agentmods](https://agentmods.dev/badge/skills/sioyooo/repogrammar/mcp-contract-change/github.svg)](https://agentmods.dev/skills/sioyooo/repogrammar/mcp-contract-change)
Your own site
<a href="https://agentmods.dev/skills/sioyooo/repogrammar/mcp-contract-change"><img src="https://agentmods.dev/badge/skills/sioyooo/repogrammar/mcp-contract-change/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 mcp-contract-change

Your own site · 80×15
<a href="https://agentmods.dev/skills/sioyooo/repogrammar/mcp-contract-change"><img src="https://agentmods.dev/badge/skills/sioyooo/repogrammar/mcp-contract-change.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 369 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00028 $0.00369
Opus 5.5 $0.00011 $0.00148
Sonnet 5.5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 2mo ago against content hash de3fb01f6ecb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-contract-change 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 2mo 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.

.agents/skills/mcp-contract-change/SKILL.md · 60 lines

What it actually says

Purpose

Protect the MCP contract while keeping transport concerns out of the domain model.

Trigger conditions

Use when changing src/rust/interfaces/mcp/, planned MCP tools, transport-neutral contract types, serialization behavior, or documented MCP error semantics.

Required reading

  • docs/specifications/mcp-api.md
  • docs/architecture/dependency-rules.md
  • docs/development/branching-and-commits.md

Preconditions

  • Decide whether the change is a major feature.
  • Confirm no MCP SDK type leaks into core.
  • Preserve the default minimal MCP surface unless an ADR changes it: repogrammar_context with explicit operations rather than multiple default pattern-family tools.

Step-by-step procedure

  1. Update the MCP specification first.
  2. Keep domain and transport types separated.
  3. Add serialization and deserialization tests when concrete schemas exist.
  4. Analyze compatibility with existing tool names and responses.
  5. Update CHANGELOG for user-visible contract changes.
  6. Add or update an ADR for breaking or durable contract decisions.

Required verification

Run formatting, clippy, tests, repository guard, and guide equality checks.

Documentation updates

Update docs/specifications/mcp-api.md, README, CHANGELOG, and ADRs as needed.

Commit requirements

Use a major-feature branch for breaking or user-visible MCP changes.

Completion report

Report changed tools, compatibility impact, tests, branch cleanup status when merged, and any deferred schema work.

Failure and rollback handling

If compatibility cannot be proven, mark the contract unstable and do not claim a stable MCP API.

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. 2mo ago First seen · 60 lines · 28 tokens per session scan A de3fb01f6ecb

Subscribe to this mod's changes

mcp-contract-change is a skill published in the GitHub repository SioYooo/RepoGrammar (0 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 369 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

architecture-audit

Systematic architecture audit and refactoring methodology for Rust + TypeScript codebases. Use when performing refactoring, cleanup, unification, code review, dead code removal, module reorganization, or tech debt elimination. Ensures no naming confusion, semantic overloading, hidden defaults, duplicate logic, or…

org2AI/ORG2 · 70 tokens

webgl-liquid-metal

A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…

nexu-io/open-design · 121 tokens

webgl-neon-grid

A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or…

nexu-io/open-design · 115 tokens

webgl-particle-galaxy

A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…

nexu-io/open-design · 126 tokens

webgl-holographic-foil

A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.

nexu-io/open-design · 41 tokens

webgl-horizontal-parallax

A horizontal-scroll WebGL gallery (Three.js): frames glide sideways with lerp smoothing and each image parallaxes its texture (UV shift) by its position in the viewport.

nexu-io/open-design · 41 tokens