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-context-architecturegit 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-context-architecture)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/copilot-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/copilot-context-architecture/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-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/copilot-context-architecture.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 | $0.00107 | $0.02156 |
| Opus 5 | $0.00053 | $0.01078 |
| Sonnet 5 | $0.00021 | $0.00431 |
| Haiku 4.5 | $0.00011 | $0.00216 |
Grade A, and why
copilot-context-architecture 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Context Architecture
GitHub Copilot's context system is a two-tier pipeline: a client-side "prompt crafter" in the IDE extension that assembles a token-budgeted Fill-in-the-Middle (FIM) prompt, and a cloud-side GitHub proxy (hosted in Azure) that performs RAG retrieval against a server-side semantic index, applies safety/IP filters, and routes to the model. Understanding this pipeline tells you exactly which levers exist for improving Copilot's context — and which internals are black boxes you should not build on.
When to Activate
Activate this skill when:
- Diagnosing why Copilot inline completions are irrelevant or ignore nearby code
- Deciding how to structure a workspace so Copilot sees the right context (open tabs, file layout, instruction files)
- Configuring
#codebase/ semantic search, repository indexing, or knowledge bases - Making enterprise governance decisions: content exclusions, training opt-outs, data residency, plan selection
- Evaluating Copilot's effective vs. advertised context window for a model
Do not activate this skill for adjacent work owned by other skills:
- Do not activate for platform-agnostic attention mechanics:
context-fundamentals. - Do not activate for Copilot CLI compaction, checkpoints, and
/context:copilot-session-management. - Do not activate for designing your own RAG pipelines:
memory-systems.
Core Concepts
Client vs. cloud division of labor
Copilot runs as a language server (Node.js/TypeScript, JSON-RPC) embedded in the IDE. For inline completions, the extension collects context and constructs the prompt locally, then ships it through the GitHub proxy. For Chat, agent, and #codebase flows, the cloud service additionally performs semantic retrieval (RAG) and intent detection. The latency-critical work — scanning open tabs, scoring snippets, packing a token budget — is all client-side.
What the extension scans
On each keystroke (after a ~75 ms debounce), Copilot extracts the prefix (code before cursor) and suffix (code after cursor), then scans:
- All open editor tabs ("neighboring tabs")
- Recently edited/accessed files (~20 most recent of the same language)
- Files in the same directory and the import graph
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 106 lines · 107 tokens per session scan A c1321a508845
copilot-context-architecture is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 2mo ago), licensed MIT. It adds 107 tokens to every session and 2,156 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.