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 skills/theam/limina/build-maintainable-softwarenpx skills add theam/limina --skill build-maintainable-softwaregit clone --depth 1 https://github.com/theam/liminaWrote 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/theam/limina/build-maintainable-software)<a href="https://agentmods.dev/skills/theam/limina/build-maintainable-software"><img src="https://agentmods.dev/badge/skills/theam/limina/build-maintainable-software.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 | $0.00058 | $0.01184 |
| Opus 5 | $0.00029 | $0.00592 |
| Sonnet 5 | $0.00012 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00118 |
Grade A, and why
build-maintainable-software 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Maintainable Software
Overview
Build code that is easy to read, easy to change, and hard to misuse. Favor clear intent, cohesive modules, explicit boundaries, predictable control flow, and tests that protect behavior without overcoupling to implementation.
Load the smallest set of references that fits the task. Do not load every reference by default.
When to use it
Use this skill when the work is mainly about:
- implementing or refactoring production code
- reviewing code for correctness, maintainability, or safe changeability
- designing module boundaries, APIs, naming, ownership, or test strategy
- simplifying an over-abstracted or fragile implementation
Do not use it when the main problem is:
- external landscape search or state-of-the-art mapping
- experiment design, baseline selection, or interpreting research evidence
- a request for broad rewrites driven mostly by style preference rather than concrete change value
Workflow
- Clarify the behavior change, not just the code change. Identify the user-facing outcome, constraints, invariants, and affected boundaries.
- Start with the simplest design that makes the intent obvious. Avoid speculative abstractions, indirection, configuration, and generalization.
- Decide boundaries before coding: ownership of state, direction of dependencies, public API surface, and locations of side effects.
- Make names reveal intent. Prefer domain terms, stable concepts, and small interfaces over generic utilities and overloaded helpers.
- Keep execution flow unsurprising. Flatten nesting, reduce control flags, isolate branching, and make data transformations explicit.
- Keep business rules close together and push framework, I/O, time, randomness, and network code to the edges when practical.
- Add or update tests at the right level for the change: unit tests for decision logic, integration tests for boundaries and wiring, end-to-end tests only for critical flows.
- Before finishing, run the final pass in references/review-checklist.md.
What ships with it
4 files beside SKILL.md 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 · 84 lines · 58 tokens per session scan A f22da69d34ea
build-maintainable-software is a skill published in the GitHub repository theam/limina (39 stars, last pushed 28d ago), licensed Apache-2.0. It adds 58 tokens to every session and 1,184 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
dspy-gepa-reflective
Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
lazarus-group
Adversary-emulation profile for Lazarus Group (G0032, aka Hidden Cobra / Diamond Sleet / Labyrinth Chollima), a North Korean RGB-linked actor conducting espionage, destructive, and financially motivated operations.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.