ownership-driven-ai-customization-architecture: Skill for Claude Code

.github/skills/oda-copilot-customization/SKILL.md

oda-copilot-customization is a skill for Claude Code, Codex from HenriqueCotta/ownership-driven-ai-customization-architecture. It costs 82 tokens per session (2,238 once invoked), scanned A, original, MIT.

A method for designing and maintaining a repository's GitHub Copilot instructions, governance files, documentation, and safeguards. It uses the Ownership-Driven AI Customization Architecture and current official Copilot guidance.

In plain words
What is it for?
Use it to audit, improve, or maintain how Copilot is configured and governed in a repository.
Why use it?
It helps find inconsistent, outdated, or unnecessarily complicated Copilot customizations. It keeps the review focused on the requested scope while addressing dependencies that would make a narrow fix incomplete.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is HenriqueCotta/ownership-driven-ai-customization-architecture's own configuration. It tells Claude Code and Codex how to work on ownership-driven-ai-customization-architecture 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 ownership-driven-ai-customization-architecture configures →

Reuse

Borrowing it

Nothing to install: this file belongs to HenriqueCotta/ownership-driven-ai-customization-architecture. 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/HenriqueCotta/ownership-driven-ai-customization-architecture/main/.github/skills/oda-copilot-customization/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/HenriqueCotta/ownership-driven-ai-customization-architecture

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 oda-copilot-customization

README.md
[![agentmods](https://agentmods.dev/badge/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization/github.svg)](https://agentmods.dev/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization)
Your own site
<a href="https://agentmods.dev/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization"><img src="https://agentmods.dev/badge/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization/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 oda-copilot-customization

Your own site · 80×15
<a href="https://agentmods.dev/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization"><img src="https://agentmods.dev/badge/skills/henriquecotta/ownership-driven-ai-customization-architecture/oda-copilot-customization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,238 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 $0.00082 $0.02238
Opus 5 $0.00041 $0.01119
Sonnet 5 $0.00016 $0.00448
Haiku 4.5 $0.00008 $0.00224

Measured 11d ago against content hash d3cc5d6fc06a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

oda-copilot-customization 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 11d 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/skills/oda-copilot-customization/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ODA Copilot Customization

Use this skill to keep a repository's Copilot customization healthy, current, and professionally reasoned.

The goal is not merely to remove the nearest inconsistency. The goal is a healthy customization map that respects local repository rules, ODA, the latest official Copilot docs, and the repository's desired level of control without overengineering.

Requested Outcome And Scope

Let the user's request define what this pass is for.

Requested outcomes:

  • surface in-scope problems, drift, or worthwhile improvements
  • think through a specific problem or decision before changing anything
  • resolve the requested scope and any follow-through needed to keep the result coherent

Scope:

  • keep the scope as narrow as the request honestly allows
  • expand scope only when a real dependency, coupled issue, or verification need would make the narrower pass misleading, incomplete, or unsafe

Let the request shape the work:

  • Stay in analysis when the user wants understanding, evaluation, or discussion.
  • Make changes only within the requested scope and what directly depends on it.
  • For broad requests, organize the work and the output in the clearest way for that request.

Treat each use of this skill as one pass. Surface what remains directly instead of managing further passes inside the skill.

This skill must be resilient to change. The platform, its documentation, its support boundaries, and the best implementation path can all change over time. Do not overfit the review to the current wording of a page, the current product menu, or the current shape of the platform. Use stable architectural principles to drive the review, then verify what the current platform can and cannot do in practice.

Required Sources

  1. ODA sources:
    • use the current upstream ODA repository directly as the authoritative source
    • repository: https://github.com/HenriqueCotta/ownership-driven-ai-customization-architecture
    • do not rely on local mirrors, archived copies, MVP snapshots, or deleted experiments as an authority for ODA
    • if the upstream ODA repository cannot be checked, treat the review as verification-blocked instead of pretending the architecture review is current
  2. Official GitHub Copilot docs:
    • discover the currently relevant official docs and official change surfaces that may affect the healthiest design at review time
    • do not assume today's doc taxonomy, feature names, or mechanism list will remain stable
    • when behavior, availability, or implementation priority may have changed recently, also check the latest official product-update, release-note, changelog, or equivalent official change surface that clarifies the current behavior
    • do not treat one static docs page as sufficient proof of the current best implementation path if newer official material indicates the platform behavior changed
    • stop broadening the search once the remaining uncertainty would no longer change the decision
  3. Local repository sources of truth, bridges, mirrors, and safeguards:
    • the current customization source of truth
    • any compatibility bridge
    • maintainer-facing mirrors of customization behavior
    • automated safeguards that validate or protect the customization map

Read the full file on GitHub · 158 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. 11d ago First seen · 158 lines · 82 tokens per session scan A d3cc5d6fc06a

Subscribe to this mod's changes

oda-copilot-customization is a skill published in the GitHub repository HenriqueCotta/ownership-driven-ai-customization-architecture (5 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 2,238 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

assessing-comprehension-debt

Measures the risk that code shipped without anyone understanding it: a teach-back attestation on high-risk changes, a risk band from changed-code complexity, diff size and whether a human explanation accompanied it, and optional AI-authorship provenance. Findings stay advisory by design. Use when an AI-assisted…

jaktestowac/awesome-copilot-for-testers · 107 tokens

scoping-change-relevance

Classifies a diff into file tags and hunk tags - new public export, new endpoint, modified auth, SQL string, migration, added dependency, touched prompt - then maps each tag to the quality practices it makes relevant, producing a defensible per-change check scope instead of running everything or guessing. Use when…

jaktestowac/awesome-copilot-for-testers · 118 tokens

github-operations

WORKFLOW SKILL — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code…

jonathan-vella/apex-accelerator · 101 tokens

communicating-quality-findings

Shapes QA output for the person who has to act on it: result and blocker in the first two lines, one decision per report, findings ordered by what they cost, the long artifact in a file and the decisions in the message, and magnitude stated in units the reader can count. Use when a report is accurate but nobody acts…

jaktestowac/awesome-copilot-for-testers · 160 tokens

attesting-manual-verification

Records human verification - code review, exploratory sessions, UAT, accessibility passes, UX and observability reviews - as dated, attributed attestations in a register, so human-centric practices stay in the quality contract without pretending to be automated checks. Use when a strategy requires verification no tool…

jaktestowac/awesome-copilot-for-testers · 103 tokens

code-review-advanced

Performs evidence-driven code review for pull requests, legacy modules, and quality-critical changes. Use when reviewing complex or multi-file changes, test automation suites, architectural refactors, or hot paths that need analysis of correctness, maintainability, security, performance, test quality, and operability…

jaktestowac/awesome-copilot-for-testers · 99 tokens