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/atheory-ai/skillex/agents-mdgit clone --depth 1 https://github.com/atheory-ai/skillexWrote 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/atheory-ai/skillex/agents-md)<a href="https://agentmods.dev/instructions/atheory-ai/skillex/agents-md"><img src="https://agentmods.dev/badge/instructions/atheory-ai/skillex/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 | $0.00564 | $0.00564 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
skillex 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
This file documents how to work in this repository.
Local development
This checkout dogfoods the current source, not a globally installed Skillex release.
- Run
make dev-binaryafter checkout. It builds.skillex/bin/skillexfrom this source tree. - Run
make dev-binaryagain after changing Go source. - Use
./.skillex/bin/skillexfor local Skillex commands (.exeon Windows).make refreshand the acceptance suite rebuild or select it automatically.
Skillex
This project uses Skillex for skill management. Use the skillex MCP server if available (preferred), otherwise use the CLI commands below.
MCP (preferred)
If the skillex MCP server is connected, use it directly:
- Start with
skillex_query(path, topic, tags, package, search, limit, cursor). It returns bounded discovery summaries, not whole skill files. - If
too_broadis true, use its candidate-scopednarrow_withfacets and suggestions to refine the query. - Use
skillex_readwith a selected resultrefand optional section id only after discovery; keep reads bounded. - MCP resources provide a skill table of contents. Do not bulk-load skill content.
CLI (fallback)
If MCP is not available, query skills via the command line. If the repository documents a local development binary, use it instead of a globally installed release:
skillex query --search "<concepts>"
skillex query --path <filepath> --limit 8
skillex query --topic <topic> --tags <tags>
skillex read --ref <ref-from-query> --section <optional-section-id>
Available scopes
- **
- .github/workflows/release.yml
- .goreleaser.yaml
- CHANGELOG.md
- Makefile
- VERSION
- cli/query.go
- cli/read.go
- docs/manual-testing.md
- internal/agents/**
- internal/packs/**
- internal/query/**
- internal/registry/**
- mcp/server.go
- test/**
- test/acceptance/pack_test.go
Available topics
golden-tests, integration, mcp, packs, registry, release-recovery, releases, repo-conventions, retrieval, testing
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.
- 5d ago First seen · 68 lines · 564 tokens per session scan A dbb4e6ca8ed2
skillex AGENTS.md is an instructions file published in the GitHub repository atheory-ai/skillex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 564 tokens to every session, about $0.0028 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).
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.
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).
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.
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.