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.
npx skills add navendubrajesh/context-management-for-agents --skill copilot-customizationgit clone --depth 1 https://github.com/navendubrajesh/context-management-for-agentsWrote 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.
[](https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/copilot-customization)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/copilot-customization"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/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.
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/copilot-customization"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/copilot-customization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.01913 |
| Opus 5 | $0.00051 | $0.00957 |
| Sonnet 5 | $0.00020 | $0.00383 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Customization
GitHub Copilot exposes a layered, file-based steering surface. These files are the only context channel the user fully controls — everything else (tab scanning, snippet ranking, retrieval) is automatic. This skill covers authoring them well: which layer to use for what, how to budget their token cost, and the failure modes that make Copilot ignore or misapply instructions.
When to Activate
Activate this skill when:
- Creating or restructuring
.github/copilot-instructions.md,.github/instructions/*.instructions.md, orAGENTS.md - Copilot ignores stated conventions, or applies rules from one part of the codebase to another
- Responses degrade after instructions grow ("instruction bloat")
- Building reusable prompt files for recurring tasks
- Configuring MCP servers for Copilot agent mode and deciding which to enable
Do not activate this skill for adjacent work owned by other skills:
- Do not activate for Copilot's internal prompt assembly, retrieval, or governance:
copilot-context-architecture. - Do not activate for CLI session compaction and checkpoints:
copilot-session-management. - Do not activate for platform-agnostic instruction-design theory:
context-fundamentals. - Do not activate for designing MCP tool schemas themselves:
tool-design.
Core Concepts
The instruction layer stack
Copilot merges instruction sources in priority order:
- Personal instructions (user-level, follow the user everywhere)
- Path-scoped instructions —
.github/instructions/<name>.instructions.mdwith anapplyToglob in YAML frontmatter; loaded only when the working file matches - Repository instructions —
.github/copilot-instructions.md; loaded into every Copilot request in the repo AGENTS.md— read by the Copilot coding agent and other AGENTS.md-conformant agent products- Organization instructions (Enterprise; apply to all org seats)
The architectural rule: put content at the narrowest layer that still covers its audience. Repo-wide invariants (build commands, naming conventions, "never edit generated files") go in copilot-instructions.md. Anything language-, directory-, or framework-specific goes in a path-scoped file so it costs zero tokens when irrelevant. This is progressive disclosure implemented with Copilot's native machinery.
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.
- 10d ago First seen · 103 lines · 102 tokens per session scan A 5ae8ae9c447a
copilot-customization is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,913 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…