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/getskillseal/skillseal/agents-mdgit clone --depth 1 https://github.com/getskillseal/skillsealWhat 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 | $0.00420 | $0.00420 |
| Opus 5 | $0.00210 | $0.00210 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
skillseal 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 2d 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.
What it actually says
Agents and SkillSeal
SkillSeal installs a skill as a plain Agent Skills
folder: a directory with a SKILL.md and optional scripts/, references/,
and assets/. Nothing about the format changes, so every agent that reads
Agent Skills reads a sealed skill with no plugin and no integration. The only
addition is the seal: one line that proves what the folder is before it lands.
How an agent gets a sealed skill
npx skillseal add sk1… # verify the line, then write the folder
skillseal add checks the line's checksum offline, verifies the publisher
signature and every file hash, and only then writes the folder into the skills
directory of each agent it finds. Discovery, activation, and execution then work
exactly as they do for any Agent Skill.
Where it installs
skillseal where lists the agents found on the machine. Out of the box it
writes to the skills folder of Claude Code and Claude Desktop, Hermes, goose,
Cursor, Codex, OpenCode, OpenHands, Letta, Amp, Gemini CLI, and GitHub Copilot.
Support for another agent is one line in skillseal/agents.mjs.
Backward compatibility
- A sealed skill is a normal Agent Skill folder. Remove SkillSeal and the folder still works.
- Name based installs keep working; the seal is additive.
- The install line is content addressed, so it resolves from any store and none has to be trusted.
Using a sealed skill as a tool
An agent can fetch, verify, and run a skill straight from storage with the same
verify then run path exposed as an MCP tool. See
demo/agent/skill-mcp.mjs and
docs/design/agent-uses-skill.md.
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.
- 2d ago First seen · 41 lines · 420 tokens per session scan A bc380e26de2e
skillseal AGENTS.md is an instructions file published in the GitHub repository getskillseal/skillseal (2 stars, last pushed 20d ago), licensed MIT. It adds 420 tokens to every session, about $0.0021 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
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
ToolRegistry AGENTS.md
Instructions for Oaklight/ToolRegistry, covering agents.md — toolregistry, what this project is, architecture, repository layout and setup and commands.
GENesis-AGI AGENTS.md
AGENTS.md instructions for WingedGuardian/GENesis-AGI, covering agent instructions, code review mandate (adversarial), gitnexus — code intelligence (advisory), genesis capability surface and skills.
gigaxity-deep-research AGENTS.md
Instructions for yoloshii/gigaxity-deep-research, covering gigaxity deep research — agent reference, tool surface, when to call which tool, environment variables and anti-patterns.
apex-accelerator instructions.instructions.md
Guidelines for creating high-quality custom instruction files for GitHub Copilot.
agent-ready-repo AGENTS.md
Instructions for eugenelim/agent-ready-repo, covering agents.md, project overview, rule lookups, documentation and development workflow.