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 leaky-abstractionsgit 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/leaky-abstractions)<a href="https://agentmods.dev/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/leaky-abstractions"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/leaky-abstractions/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/leaky-abstractions"><img src="https://agentmods.dev/badge/skills/the-artificer-of-ciphers-llc/skills-from-the-artificer/leaky-abstractions.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 | $0.00126 | $0.00801 |
| Opus 5.5 | $0.00050 | $0.00320 |
| Sonnet 5.5 | $0.00025 | $0.00160 |
| Haiku 4.5 | $0.00013 | $0.00080 |
Grade A, and why
leaky-abstractions 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Law of Leaky Abstractions
"All non-trivial abstractions, to some degree, are leaky." — Joel Spolsky, 2002
The core idea
An abstraction is a simplification: it hides complexity and lets you work at a higher level. TCP hides the complexity of packet routing. An ORM hides the complexity of SQL. A garbage collector hides the complexity of memory management.
But all non-trivial abstractions eventually fail to hide everything. The underlying complexity leaks through — and when it does, you need to understand both the abstraction and the thing it was supposed to abstract.
This is not a solvable problem. It is a fundamental property of abstraction.
Classic examples
TCP over lossy networks: TCP presents a "reliable pipe" abstraction. But if the network is slow or lossy, TCP's retry behavior becomes visible through degraded performance. To reason about the slowdown, you need to understand TCP internals.
ORMs: SQL ORMs promise you don't need to write SQL. But an ORM that generates a SELECT N+1 query pattern will be slow, and diagnosing it requires understanding the SQL being generated — which the ORM was meant to hide.
Iterating over a large file in a high-level language: The abstraction promises "just loop over lines." But if the file is huge and you run out of memory, you need to understand buffering, paging, and how the OS reads files.
Remote procedure calls (RPCs): RPC frameworks promise "call a remote function like a local one." But network failures, latency, and partial failure modes mean you can't treat remote calls like local ones.
What to do about it
Know your abstractions well enough to debug them. When an abstraction fails, you will need to descend. Learn enough about the layer below your abstraction to reason about its behavior when it bleeds through.
Don't assume abstractions protect you from the underlying complexity. A developer using an ORM still benefits from understanding SQL. A developer using a cloud storage service still benefits from understanding object storage semantics. The abstraction is a productivity tool, not a knowledge substitute.
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 · 53 lines · 126 tokens per session scan A 3949eb3145d0
leaky-abstractions 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 126 tokens to every session and 801 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
incident-postmortem
Escribe un postmortem de incidente estructurado o revisión post-incidente. Úsalo cuando se te pida escribir un postmortem, reporte de incidente, revisión P1/P2, reporte de apagón o RCA (análisis de causa raíz). Produce un postmortem sin culpables con cronología, causa raíz, factores contribuyentes, resumen de impacto…
agent-incident-postmortem
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective…
agent-design-review
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools…
prompt-debugging
Figure out why a prompt isn't working and fix it — diagnose the actual failure (ambiguity, missing context, wrong format, conflicting instructions) instead of randomly rewording. Use when asked why isn't my prompt working, the AI keeps ignoring my instructions, my prompt gives inconsistent results, or how do I fix…
prompt-optimizer
Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to improve a prompt, fix a prompt that gives inconsistent or wrong results, reduce hallucination/refusals, or make output follow a format. Produces a rewritten prompt with a diagnosis of what was failing…
rag-architecture-review
Review an existing Retrieval-Augmented Generation system and find why it underperforms. Use when asked to review or audit a RAG pipeline, diagnose wrong/ungrounded answers from a 'chat with your docs' feature, or improve an already-built knowledge assistant. Produces a staged review — ingestion, chunking, retrieval…