skill-up is a tool for evaluating and improving Agent Skills through declarative test cases, multiple agent engines, configurable judges, and structured reports. Developers and agent builders use it locally or in continuous integration to measure skill quality and iterate on failures. The catalogue entries are skills and instructions that can be evaluated or evolved with it.
Borrowing it
Nothing to install: this file belongs to alibaba/skill-up. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/alibaba/skill-up/main/AGENTS.mdgit clone --depth 1 https://github.com/alibaba/skill-upWrote 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/alibaba/skill-up/agents-md)<a href="https://agentmods.dev/instructions/alibaba/skill-up/agents-md"><img src="https://agentmods.dev/badge/instructions/alibaba/skill-up/agents-md/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/instructions/alibaba/skill-up/agents-md"><img src="https://agentmods.dev/badge/instructions/alibaba/skill-up/agents-md.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 | $0.02490 | $0.02490 |
| Opus 5.5 | $0.00996 | $0.00996 |
| Sonnet 5.5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
skill-up AGENTS.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 15d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file follows the agents.md convention and provides machine-readable guidance for AI coding agents (Qoder, Claude Code, Codex, Cursor, etc.) working in this repository. For a human-oriented overview, see
README.mdandCONTRIBUTING.md.
Project overview
skill-up is a CLI evaluation framework for Agent Skill developers, written
in Go. It loads declarative eval configs (evals/eval.yaml + cases/*.yaml),
provisions an isolated workspace, invokes an Agent Engine (Qoder CLI / Claude
Code / Codex), runs Judges (rule_based / script / agent_judge), and emits
structured reports (JSON / JUnit / HTML / Anthropic grading.json).
- Module path:
github.com/alibaba/skill-up - Entry point:
cmd/skill-up/main.go - Go version: 1.26+ (see
go.mod) - License: Apache-2.0
Setup commands
# Fetch dependencies (only needed after cloning or go.mod changes)
go mod download
# Install git hooks (pre-commit + commit-msg). Idempotent; auto-runs on first build.
make hooks
# Install pinned lint tools into .tools/bin/ (golangci-lint v2.11.4, revive v1.10.0)
make lint-tools
If you are in mainland China and go install is slow, set
GOPROXY=https://goproxy.cn,direct before running the commands above.
On Windows, make is unavailable by default; use the PowerShell equivalents
in scripts/windows/ (hooks.ps1, lint-tools.ps1, verify.ps1). See the
Windows support guide for supported features and
known limitations.
Build & run
# Standard build with version injection via ldflags -> bin/skill-up
make build
# Fast iteration build (no version injection)
go build -o bin/skill-up ./cmd/skill-up
# Run the CLI
./bin/skill-up --help
./bin/skill-up run ./evals/eval.yaml
./bin/skill-up validate ./evals/eval.yaml
Testing
# Unit tests (race detector enabled — always use this)
make test
# equivalent: go test -race ./...
go test -race ./...
# GitHub Action adapter tests (requires Python 3)
make test-action
# Run a single test
go test -race -run TestFoo ./internal/config/
# End-to-end tests (build-tag gated, slower)
make e2e
# equivalent: go test -tags e2e -v ./e2e
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.
- 15d ago Changed f39ade73cb9d
- 1mo ago Changed · +18 tokens per session f44d3b12f267
- 1mo ago Changed · +4 lines · +59 tokens per session 53105abd858f
- 2mo ago Changed · +2 lines · +34 tokens per session dd7bc96ba345
- 2mo ago First seen · 225 lines · 2,379 tokens per session scan A eae4818d1f86
skill-up AGENTS.md is an instructions file published in the GitHub repository alibaba/skill-up (1,420 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,490 tokens to every session, about $0.0100 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 2026-08-30.
skill-up AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-up AGENTS.mdalibaba/skill-up | Instructions file | 1.4k | yesterday | Apache-2.0 | A | 2,490 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |