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 skills add The-Artificer-of-Ciphers-LLC/skills-from-the-artificer --skill hyrums-lawgit clone --depth 1 https://github.com/The-Artificer-of-Ciphers-LLC/skills-from-the-artificerWrote 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/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/hyrums-law)<a href="https://agentmods.dev/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/hyrums-law"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/hyrums-law/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/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/hyrums-law"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/hyrums-law.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 | $0.00115 | $0.00841 |
| Opus 5.5 | $0.00046 | $0.00336 |
| Sonnet 5.5 | $0.00023 | $0.00168 |
| Haiku 4.5 | $0.00012 | $0.00084 |
Grade A, and why
hyrums-law 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyrum's Law
"With a sufficient number of users of an API, it does not matter what you promise in the contract: all observable behaviors of your system will be depended on by somebody." — Hyrum Wright, 2012
The core idea
If enough people use your API, every behavior — documented or not, intentional or not, even bugs — will be depended upon by someone. Your documented interface is not the real interface. The real interface is everything observable: response times, error message text, ordering of results, whitespace in JSON output, HTTP headers, memory usage patterns.
This has a humbling implication: as an API grows, your ability to change anything without breaking someone approaches zero.
Why it matters
When you're building for a small set of users, you can coordinate changes. When your API is used by thousands of developers, you can't know what they've built. Some of them will have:
- Parsed your error messages with regex
- Depended on the alphabetical ordering of a field that you return in hash order
- Built retry logic around your specific timeout behavior
- Cached responses based on headers you didn't intend to be cacheable
- Worked around a bug in a way that breaks when you fix the bug
Real-world examples
- Python 2→3 migration: even behavior never in the spec was depended on
- Google's web infrastructure: engineers found users depending on specific memory layouts and response ordering
- Any bug fix that "breaks" existing users who had worked around it
How to design defensively
Minimize observable surface area. The less you expose, the less gets depended on. Keep internals genuinely internal. Be deliberate about what is observable versus what is an implementation detail.
Version your APIs.
Versioning is the escape hatch. When you need to change behavior, version the API and give users a migration path. /v1/ and /v2/ coexist; users migrate on their timeline.
Deprecate slowly and loudly. Give users long warning periods before removing or changing behavior. Emit deprecation warnings in responses. Document the change prominently. Provide migration guides.
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 · 60 lines · 115 tokens per session scan A ee6a096dda4d
hyrums-law is a skill published in the GitHub repository The-Artificer-of-Ciphers-LLC/skills-from-the-artificer (6 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 841 once invoked, about $0.0005 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 skills, from other repositories
offensive-api-abuse
Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query…
offensive-graphql
Offensive methodology for attacking GraphQL APIs during penetration tests and bug bounty engagements. Covers the full attack lifecycle: endpoint discovery, introspection abuse and blind schema reconstruction when introspection is disabled, authentication and authorization bypass through Relay node IDs and nested…
agent-readiness-audit
Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready, to audit a site or API for AI usability, to prepare for agentic traffic, or when agents keep failing against your…
mcp-server-spec
Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents. Use when asked to spec an MCP server, expose a product to agents, design tools for Claude or other MCP clients, or review why an existing MCP server performs badly. Produces a complete…
api-docs-writer
Escribe documentación clara y orientada a desarrolladores. Úsalo cuando se te pida documentar un endpoint de API, escribir docs de referencia de API, crear una guía de desarrollador, o convertir una especificación cruda o colección Postman en documentación. Produce documentación de endpoint con descripciones…
api-security-best-practices
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.