agentmods.dev

Sklm AGENTS.md

Sklm AGENTS.md is an instructions file for Codex, OpenCode from Auran0s/Sklm. It costs 1,443 tokens per session, scanned A, original, MIT.

Project instructions for Sklm, a Python command-line tool that installs and manages coding-agent skills.

In plain words
What is it for?
Setting up Sklm, running its tests, understanding its command-line entry point, and locating its global and project-specific skill files.
Why use it?
They give an agent the commands, file layout, entry point, and storage locations it needs to work on the project correctly.

Instructions file for CodexOpenCode

not rated 10 4d ago A scan 1,443 tokens original MIT
View the source file Auran0s/Sklm
Install

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.

agentmods
npx agentmods add instructions/auran0s/sklm/agents-md
Clone the repo
git clone --depth 1 https://github.com/Auran0s/Sklm

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.

agentmods badge for Sklm AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/auran0s/sklm/agents-md.svg)](https://agentmods.dev/instructions/auran0s/sklm/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/auran0s/sklm/agents-md"><img src="https://agentmods.dev/badge/instructions/auran0s/sklm/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,443 This file is loaded in full into every session.
When invoked 1,443 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01443 $0.01443
Opus 5 $0.00722 $0.00722
Sonnet 5 $0.00289 $0.00289
Haiku 4.5 $0.00144 $0.00144

Measured 4d ago against content hash 8d58268bc76a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Sklm 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.

AGENTS.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Sklm

Setup & dev commands

pip install sklm-cli                  # install from PyPI
pip install -e .                  # editable install (development)
pip install -r requirements.txt   # pytest + pytest-cov
python3 -m pytest tests/          # run all tests (single file: tests/test_sklm.py)
python3 -m pytest tests/ -k <pattern>  # run a subset

No CI, no linting, no typechecking. Single test file, no tests/__init__.py.

Entrypoint

  • CLI: sklm.cli.main:run (Typer app, no_args_is_help=True).
  • Declared in pyproject.toml under [project.scripts].
  • Version derived from importlib.metadata.version("sklm") in sklm/__init__.py.

Architecture

Two-level store:

~/.sklm/                   # global store (~/.sklm/ or $SKLM_HOME)
  store/skills/            #   installed skill dirs (each has SKILL.md)
  config.yaml              #   GlobalConfig — resource catalog + telemetry
  registries.yaml          #   RegistrySource entries
  cache/                   #   shallow-cloned git repos for install --from

./.sklm/                   # per-project workspace (gitignored)
  links/skills/            #   symlinks → ~/.sklm/store/skills/
  sklm.yaml                #   WorkspaceConfig (agents, resources, links)

sklm add pipeline: resolve → store → link → sync (copy + variant overlay) to agent config.

Note: .sklm/ is in .gitignore — the per-project workspace is intentionally never committed.

Source layout

Path Role
sklm/api.py Sklm facade — wires everything
sklm/cli/main.py Typer CLI — all commands
sklm/cli/wizard.py Interactive prompt and state detection
sklm/models/__init__.py Pydantic v2 models, YAML persistence
sklm/store/__init__.py GlobalStore — ~/.sklm/ management
sklm/core/workspace.py Workspace — .sklm/ management
sklm/core/registry.py RegistryManager — clone/fetch, search
sklm/core/crud.py Resource CRUD (resolve → store → link)
sklm/core/linking.py Symlink create/remove/repair
sklm/core/update.py UpdateChecker — GitHub API version check
sklm/agents/agents.yaml Source of truth — 30 agent definitions (dir_name, detect mode)
sklm/agents/base.py Abstract AgentAdapter — base class for all adapters
sklm/agents/_sync.py Shared sync logic with variants/<agent>/ overlay
sklm/agents/generic.py GenericAdapter — handles 28 auto-detect agents
sklm/agents/github_copilot.py GitHubCopilotAdapter — custom (detect: explicit)
sklm/agents/registry.py AgentRegistry — discovery + adapter lookup
sklm/telemetry.py UmamiTracker — daemon thread, 2s timeout

Read the full file on GitHub · 105 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.

  1. 4d ago First seen · 105 lines · 1,443 tokens per session scan A 8d58268bc76a

Subscribe to this mod's changes

Sklm AGENTS.md is an instructions file published in the GitHub repository Auran0s/Sklm (10 stars, last pushed 4d ago), licensed MIT. It adds 1,443 tokens to every session, about $0.0072 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.

agentai-agentsclaude-codeclimanagementskills
Related

Other instructions, from other repositories

webflow-skills CLAUDE.md

Claude Code instructions for webflow/webflow-skills, covering project overview, repository structure, ci validation, what ci checks and 2. marketplace and plugin configs exist.

webflow/webflow-skills · 735 tokens

rolecraft AGENTS.md

Instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.

rolecraft-sh/rolecraft · 845 tokens

MathModelAgent CLAUDE.md

Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.

jihe520/MathModelAgent · 1,377 tokens

lime AGENTS.md

AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.

limecloud/lime · 1,517 tokens

clean-code-skills clean-code.instructions.md

Instructions for btseee/clean-code-skills, covering clean-code instructions, clean code rules (clean-code-skills), work loop, dependency direction and file and code placement.

btseee/clean-code-skills · 1,289 tokens

wtcraft CLAUDE.md

Instructions for zywkloo/wtcraft, covering wtcraft routing, repo structure (wtcraft dogfooding), model knowledge policy and release guardrails.

zywkloo/wtcraft · 295 tokens