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 agentmods add instructions/pratikxpanda/agentskills-sdk/copilot-instructionsgit clone --depth 1 https://github.com/pratikxpanda/agentskills-sdkWrote 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/instructions/pratikxpanda/agentskills-sdk/copilot-instructions)<a href="https://agentmods.dev/instructions/pratikxpanda/agentskills-sdk/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/pratikxpanda/agentskills-sdk/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.02125 | $0.02125 |
| Opus 5 | $0.01063 | $0.01063 |
| Sonnet 5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
agentskills-sdk copilot-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 4d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
Poetry monorepo. Ten packages, versioned and released together.
| Path | Package |
|---|---|
packages/core/agentskills-core |
Registry, SkillProvider ABC, spec validation. Only dependency is pyyaml. |
packages/adapters/agentskills-adapters |
Import common agent instruction formats as native skills |
packages/providers/agentskills-fs |
Local filesystem provider |
packages/providers/agentskills-http |
Static HTTP / CDN provider |
packages/integrations/agentskills-langchain |
LangChain tools |
packages/integrations/agentskills-agentframework |
Microsoft Agent Framework context provider |
packages/integrations/agentskills-mcp-server |
MCP server + Agent Framework MCP bridge |
packages/retrieval/agentskills-retrieval |
Query-time skill selection: BM25 and embedding rankers |
packages/tools/agentskills-tools |
agentskills command: init, validate, lint, inspect, serve |
packages/testing/agentskills-testing |
Provider conformance suite, InMemorySkillProvider, pytest fixtures |
Planning lives in docs/ROADMAP.md, per-milestone specs in docs/issues/, settled
decisions in docs/adr/.
Branch workflow
Never commit to main. For every unit of work:
git checkout main
git pull --prune
git checkout -b <type>/<slug> # fix/ feat/ perf/ docs/ chore/
# implement, test, lint
git push -u origin <branch>
The maintainer merges pull requests manually. Do not create, update, or comment on
issues or pull requests, and do not use the gh CLI for that. After a merge, sync
main and cut a fresh branch for the next item.
One roadmap item — or one tightly coupled cluster — per branch. If scope drifts, rename the branch or squash-merge under a title that matches what actually landed.
Labels
Releases are built with generate_release_notes: true, which groups merged pull requests
by the label map in .github/release.yml. The label is the only input — the branch
prefix and commit message are ignored. An unlabelled pull request lands under "Other
Changes", which is where most of 0.3.0 ended up.
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.
- 4d ago First seen · 143 lines · 2,125 tokens per session scan A 35e004545a30
agentskills-sdk copilot-instructions.md is an instructions file published in the GitHub repository pratikxpanda/agentskills-sdk (23 stars, last pushed 8d ago), licensed MIT. It adds 2,125 tokens to every session, about $0.0106 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 2026-08-30.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.