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/andylin-hao/agent-codewalk/agents-mdgit clone --depth 1 https://github.com/andylin-hao/agent-codewalkWrote 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/andylin-hao/agent-codewalk/agents-md)<a href="https://agentmods.dev/instructions/andylin-hao/agent-codewalk/agents-md"><img src="https://agentmods.dev/badge/instructions/andylin-hao/agent-codewalk/agents-md.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 | $0.01840 | $0.01840 |
| Opus 5 | $0.00920 | $0.00920 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
agent-codewalk 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 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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the operating contract for coding agents working in Agent CodeWalk. Read it
before changing the repository. Human contributors should also read
CONTRIBUTING.md.
Product intent
Agent CodeWalk is a local-first VS Code/Cursor extension paired with a Rust MCP companion. It turns an agent's code change or code explanation into a navigable walkthrough whose steps open and highlight real source blocks in the editor.
Protect these product promises in every change:
- Walkthroughs are trustworthy: a normal change walkthrough covers every text diff hunk.
- Navigation is safe: stale or ambiguous anchors never highlight a guessed location.
- User code and explanations stay local unless a separately approved design says otherwise.
- Integration setup is transparent, reversible, and limited to resources the extension owns.
- The editor and companion agree on one versioned walkthrough contract.
- User-facing behavior is understandable in both English and Simplified Chinese.
Do not add telemetry, network access, model API calls, or remote content loading without a separate user-approved design and an explicit privacy and security update.
Repository map
| Area | Responsibility |
|---|---|
protocol/walkthrough-v1.schema.json |
Canonical persisted-session contract |
protocol/fixtures/ |
Shared positive and negative protocol examples |
crates/agent-codewalk-mcp/ |
Rust MCP transport, baseline capture, diff coverage, validation, and atomic publication |
extension/src/ |
VS Code activation, storage, validation, navigation, highlighting, webview, localization, and integration setup |
extension/resources/agent-codewalk/SKILL.md |
Portable instructions installed for supported agents |
extension/package.json and package.nls*.json |
Marketplace metadata, commands, settings, keybindings, and localized manifest text |
scripts/ |
Cross-project version synchronization and integration diagnostics |
.github/workflows/ |
CI, pull-request policy, platform packaging, registry publishing, and GitHub releases |
docs/ |
Architecture, troubleshooting, publishing, release acceptance, and roadmap |
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 · 186 lines · 1,840 tokens per session scan A f43c9b824fd3
agent-codewalk AGENTS.md is an instructions file published in the GitHub repository andylin-hao/agent-codewalk (2 stars, last pushed 9d ago), licensed MIT. It adds 1,840 tokens to every session, about $0.0092 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 instructions, from other repositories
Think-In-HTML CLAUDE.md
Instructions for vibhusharma101/Think-In-HTML, covering think-in-html, blocks mode (--blocks) — legacy templated engine, commands, build / validate and key rules.
code-lens AGENTS.md
AGENTS.md instructions for j0hanz/code-lens, covering agents.md, tooling, architecture, testing strategy and commands.
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.