Borrowing it
Nothing to install: this file belongs to Auran0s/Sklm. 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/Auran0s/Sklm/main/AGENTS.mdgit clone --depth 1 https://github.com/Auran0s/SklmWrote 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/auran0s/sklm/agents-md)<a href="https://agentmods.dev/instructions/auran0s/sklm/agents-md"><img src="https://agentmods.dev/badge/instructions/auran0s/sklm/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/auran0s/sklm/agents-md"><img src="https://agentmods.dev/badge/instructions/auran0s/sklm/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 | $0.01443 | $0.01443 |
| Opus 5.5 | $0.00577 | $0.00577 |
| Sonnet 5.5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00144 | $0.00144 |
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 1mo 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 — 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.tomlunder[project.scripts]. - Version derived from
importlib.metadata.version("sklm")insklm/__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 |
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.
- 1mo ago First seen · 105 lines · 1,443 tokens per session scan A 8d58268bc76a
Sklm AGENTS.md is an instructions file published in the GitHub repository Auran0s/Sklm (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,443 tokens to every session, about $0.0058 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.