What is superskill AGENTS.md?

Repository instructions for superskill, a project related to obsidian-mcp. The input mentions project structure, commands, architecture, and recurring coding patterns.

Understanding the project overview, running its commands, and following its architecture and established patterns.

They give a coding agent project-specific guidance when working in that repository.

How permanu/superskill configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to permanu/superskill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/permanu/superskill/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/permanu/superskill

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/permanu/superskill/agents-md/github.svg)](https://agentmods.dev/instructions/permanu/superskill/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/permanu/superskill/agents-md"><img src="https://agentmods.dev/badge/instructions/permanu/superskill/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/permanu/superskill/agents-md"><img src="https://agentmods.dev/badge/instructions/permanu/superskill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,267 This file is loaded in full into every session.

When invoked 1,267 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.01267	$0.01267
Opus 5.5	$0.00507	$0.00507
Sonnet 5.5	$0.00253	$0.00253
Haiku 4.5	$0.00127	$0.00127

Measured 6d ago against content hash 96fc369c5dd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

superskill 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.

AGENTS.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SuperSkill — AGENTS.md

Project Overview

Universal Agentic Knowledge Base — the superskill CLI and MCP server backed by an Obsidian vault (~/Vaults/ai/) that serves as shared memory for AI coding tools. It routes tasks through curated in-repo packs and deterministic rules. skills.sh is used only by the opt-in third-party skill installer, not by default routing.

Commands

Build: npm run build (TypeScript → dist/)
Dev: npm run dev (build + watch via tsc --watch)
Lint: npm run lint (type check only: tsc --noEmit)
Test: npm test (fresh runtime/grammar build, then Vitest)
Focused tests: npx vitest run <files> --maxWorkers=2 (no rebuild; build first for tests that spawn the compiled CLI/MCP)
Coverage: npm run test:coverage (fresh build and existing coverage thresholds)

Architecture

src/cli.ts — Commander.js CLI entry point
src/mcp-server.ts — MCP server (stdio transport)
src/commands/ — Command modules (pure async functions, shared by CLI + MCP)
src/commands/skill/ — Skill commands (init, activate, validate, status, index)
src/core/ — Command infrastructure (registry, types)
src/lib/ — Library modules (vault-fs, frontmatter, search-engine, etc.)
src/lib/graph/ — Knowledge graph (schema, store, loader, router, learner)
src/lib/skills-sh/ — Skills.sh client (client), used by the opt-in installer
src/config.ts — Configuration + resolveProject() utility

Key Patterns

Unified command interface: Every command takes (args, ctx: CommandContext) where ctx bundles vaultFs, vaultPath, config, sessionRegistry, and log.
Graph-driven routing: task → router → loader → security gate → content. A per-checkout graph in the gitignored .superskill/ directory records project stack, routed skills, and activation history; default routing uses the curated in-repo catalog.
3-phase loading: INDEX (project metadata + skill list) → NEIGHBORHOOD (co-activations + recent sessions) → CONTENT (actual SKILL.md files). Each phase is optional and can be skipped.
Skills.sh is opt-in: only skill install <owner>/<repo> queries skills.sh (skill list + gen/socket/snyk audits). The default catalog and routing never scrape it — skill init indexes the in-repo catalog. If skills.sh is unreachable, GitHub fallback requires --allow-unaudited and marks the install .unaudited-superskill; empty skills.sh results refuse the fallback.
Dual interface: Every command works via both CLI and MCP. Commands are pure async functions.
Sandboxed filesystem: VaultFS enforces path validation, symlink escape detection, traversal rejection.
Lazy singletons: Graph store and the skills.sh client (opt-in installer path) are initialized on first use.
Atomic operations: Graph writes use tmpfile + rename. Session lockfiles use O_CREAT | O_EXCL.
Project detection: Auto-detected from CWD via project-map.json and git root. Use resolveProject() helper.
Auto-numbering: ADRs, tasks, learnings use NNN-<slug>.md pattern via auto-number.ts.

Read the full file on GitHub · 89 lines

Changes

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 Changed · +5 lines · +156 tokens per session 96fc369c5dd5
13d ago Changed · -1 lines · +20 tokens per session 64b5e3910433
1mo ago First seen · 85 lines · 1,091 tokens per session scan A 50f969aa62ca

Subscribe to this mod's changes

superskill AGENTS.md is an instructions file published in the GitHub repository permanu/superskill (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,267 tokens to every session, about $0.0051 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 2026-08-31.

Claude Code ai-coding codex cursor mcp mcp-server

plugin-files-mode

Rosetta Plugin Mode Bootstrap.

griddynamics/rosetta · 236 tokens

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).

microsoft/vscode · 9,649 tokens

superskill: Instructions file for Codex