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/ypolon7kiy/akashi/agents-mdgit clone --depth 1 https://github.com/ypolon7kiy/akashiWrote 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/ypolon7kiy/akashi/agents-md)<a href="https://agentmods.dev/instructions/ypolon7kiy/akashi/agents-md"><img src="https://agentmods.dev/badge/instructions/ypolon7kiy/akashi/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 5.1 | $0.01034 | $0.01034 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
akashi 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 6d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidelines (Akashi)
This file orients LLM agents working in the Akashi codebase. It summarizes structure and conventions; respect domain boundaries and layers.
Project
Akashi is a DDD-style VS Code extension in TypeScript. Extension host code lives under src/, organized by domains (then by layers such as domain, application, infrastructure, and optional ui). Domains with a webview panel have a webview/ folder for browser-side UI (e.g. React). App-level UI (e.g. the sidebar) is in src/sidebar/; shared webview bridge utilities are in src/webview-shared/, with feature-specific message contracts co-located with their bridge modules. Bundling is done with esbuild (esbuild.config.mjs): one bundle for the extension, one or more for webviews → dist/webview/<name>/.
Code map
- Domains —
src/domains/. Includesgraph(ui/,webview/graph2d/for the 2D panel) andsources(workspace source indexing; same layer rules as other domains, no domainui/orwebview/yet). - Shared code —
src/shared/(types, utils, vscode helpers, cross-domain contracts). - Sidebar —
src/sidebar/(app-level webview and host wiring). - Webview bridge — shared bridge utilities in
src/webview-shared/; feature-specific message contracts in bridge modules such assrc/sidebar/bridge/messages/andsrc/domains/graph/webview/graph2d/messages.ts.
Conventions (summary)
- Domains must not import from each other. Use
src/shared/for contracts (interfaces, types, event shapes) and inject dependencies at the application layer; composition happens inextension.tsor a small bootstrap module. - Layers: domain (pure business logic, no
vscode) → application (use cases) → infrastructure (adapters), with optional ui (commands, views, webviews) when a domain exposes host-side interactions. Webview code runs in the browser and is bundled separately; it uses shared bridge helpers fromsrc/webview-shared/, while message contracts are defined per feature bridge. - When adding or changing code, follow the conventions below and match patterns in neighboring layers and folders.
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.
- 6d ago First seen · 40 lines · 1,034 tokens per session scan A 23157bc17acd
akashi AGENTS.md is an instructions file published in the GitHub repository ypolon7kiy/akashi (3 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,034 tokens to every session, about $0.0052 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
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).
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.
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).
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.