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/j-256/agent-skills/agents-mdgit clone --depth 1 https://github.com/j-256/agent-skillsWrote 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/j-256/agent-skills/agents-md)<a href="https://agentmods.dev/instructions/j-256/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/j-256/agent-skills/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 | $0.01855 | $0.01855 |
| Opus 5 | $0.00928 | $0.00928 |
| Sonnet 5 | $0.00371 | $0.00371 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
agent-skills 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.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository-specific guidance for coding agents working on this Agent Skills repository. Keep platform-wide preferences in the user's global instructions rather than duplicating them here.
Repository overview
This repository distributes five Agent Skills as three self-contained Agent Plugins:
plugins/dsc/containsdsc-endpoint-help,dsc-scenario,dsc-scrape, their shared runtime, tests, documentation, and examplesplugins/fork-and-pr/contains thefork-and-prskill and its exampleplugins/stepped-demo-script/contains thestepped-demo-scriptskill, examples, template, and reference material
The DSC family works against Salesforce API references on developer.salesforce.com. See plugins/dsc/docs/dsc-skills.md for its architecture, boundaries, coverage, and extension guidance.
Documentation and compatibility
The plugin directories under plugins/ are canonical. Edit skill source files there. The editable DSC runtime source is plugins/dsc/shared/.
Root directories under skills/ are generated, self-contained copies for direct skill consumers. Do not edit them. Run node scripts/sync-standalone-skills.mjs --write after changing a canonical skill or the DSC runtime; check mode rejects missing, extra, changed, executable-mode-different, or symlinked generated entries. Repository-wide documentation and indexes live under docs/; package-specific documentation and examples stay with their canonical plugin skills. Link repository documentation to canonical plugin files instead of generated root copies.
Each plugin carries three manifests whose identity, version, description, and license must stay synchronized:
plugin.jsonfor the portable Agent Plugins specification.codex-plugin/plugin.jsonfor Codex.claude-plugin/plugin.jsonfor Claude Code
The root VERSION file owns the aggregate repository release version. It is independent from the package-specific plugin versions, which may diverge from one another and from the repository release train.
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.
- 4d ago First seen · 152 lines · 1,855 tokens per session scan A 76092aea6913
agent-skills AGENTS.md is an instructions file published in the GitHub repository j-256/agent-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 1,855 tokens to every session, about $0.0093 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-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.