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.
git clone --depth 1 https://github.com/itallstartedwithaidea/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/plugins/itallstartedwithaidea/agent-skills/claude-mythos-skills)<a href="https://agentmods.dev/plugins/itallstartedwithaidea/agent-skills/claude-mythos-skills"><img src="https://agentmods.dev/badge/plugins/itallstartedwithaidea/agent-skills/claude-mythos-skills/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/plugins/itallstartedwithaidea/agent-skills/claude-mythos-skills"><img src="https://agentmods.dev/badge/plugins/itallstartedwithaidea/agent-skills/claude-mythos-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
claude-mythos-skills 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.
What it actually says
{
"name": "claude-mythos-skills",
"description": "10 Claude-specific skills: prompt architecture, context engineering, tool mastery, self-healing agents, verification loops, cognitive scaffolding",
"source": "./",
"strict": false,
"skills": [
"./skills/claude-mythos/prompt-architecture",
"./skills/claude-mythos/context-engineering",
"./skills/claude-mythos/anthropic-tool-mastery",
"./skills/claude-mythos/cognitive-scaffolding",
"./skills/claude-mythos/verification-loops",
"./skills/claude-mythos/self-healing-agents",
"./skills/claude-mythos/adversarial-resilience",
"./skills/claude-mythos/agent-instinct-system",
"./skills/claude-mythos/session-archaeology",
"./skills/claude-mythos/multi-harness-portability"
]
}What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 309 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill anthropic-tool-mastery A 28 tokens
- Skill cognitive-scaffolding A 38 tokens
- Skill context-engineering A 19 tokens
- Skill multi-harness-portability A 50 tokens
- Skill prompt-architecture A 14 tokens
- Skill self-healing-agents A 27 tokens
- Skill session-archaeology A 37 tokens
- Skill verification-loops A 21 tokens
- Skill adversarial-resilience B 39 tokens
- Skill agent-instinct-system C 36 tokens
What ships with it
1 file beside marketplace.json#claude-mythos-skills in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 18 lines scan A 1fc871ab221c
claude-mythos-skills is a plugin published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
minimax
MiniMax M-series production wiring: OpenAI-compat quirks, hybrid prompt caching, Tier F quant agentic stack, model-upgrade detection. Distilled from a 41-iteration M2.7-highspeed exploration campaign.
prompt-coach
Analyzes each prompt you submit against a tiered ruleset of prompting best practices; nudges you toward better prompts (definition-of-done, scoped references, guardrails, verification steps) and quietly graduates rules you consistently follow.
claude-meta-tools
Prompt tooling for Claude Code: write and audit prompts (meta-prompt, prompt-coach, prompt-health) and introspect how the harness executes them (dump-system-prompt, explain-workflow).
prompt-template-wizard
Collect and validate all required fields for a complete implementation prompt template.
promptkitty
Assemble PromptKit prompts and author provider-native agent instructions.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.