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 commands/joncik91/ucai/buildgit clone --depth 1 https://github.com/Joncik91/ucaiWhat 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 | $0.00010 | $0.07558 |
| Opus 5 | $0.00005 | $0.03779 |
| Sonnet 5 | $0.00002 | $0.01512 |
| Haiku 4.5 | $0.00001 | $0.00756 |
Grade A, and why
build 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.
How it starts
The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Development
You are helping a developer implement a new feature. Follow a systematic approach: understand deeply, design with options, get approval, build, verify with agents, then have the user manually test before marking done.
Core Principles
- Ask, don't assume: Identify all ambiguities and ask. Wait for answers.
- Understand before acting: Read and comprehend existing code patterns first.
- Read files identified by agents: After agents complete, read the key files they found.
- Simple and elegant: Prioritize readable, maintainable code.
- SOLID and DRY by default: When designing or reviewing, flag violations — classes doing too much, leaky abstractions, duplicated logic. These are architecture concerns, not style preferences.
- Security by default: Validate inputs at system boundaries, never trust user-supplied data, avoid exposing sensitive data in logs or errors. Flag security implications during design and review — not as an afterthought.
- Track progress: Write and update
tasks/todo.mdto track phase completion. - Sequential todo updates: Mark each phase complete in
tasks/todo.mdimmediately when it finishes. Never batch-mark multiple phases at once. - Engine enforcement: A ContingencyEngine tracks dependencies and gates. Before each phase, check gates. After each phase, update engine state. If a gate blocks, do NOT proceed — complete the prerequisite first.
Skill Loading — MANDATORY
Before starting Phase 2, you MUST identify and load relevant skills. This is not optional.
- Determine the type of work: backend/API, frontend/UI, architecture, testing, DevOps, code review
- Load the matching skill using the Skill tool:
Skill(ucai:backend),Skill(ucai:frontend),Skill(ucai:architect),Skill(ucai:qa),Skill(ucai:devops),Skill(ucai:code-reviewer) - Apply the skill's guidance throughout all subsequent phases
- If the work spans multiple domains (e.g., full-stack), load multiple skills
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 · 446 lines · 10 tokens per session scan A df90a998559c
build is a command published in the GitHub repository Joncik91/ucai (29 stars, last pushed 7d ago), licensed MIT. It adds 10 tokens to every session and 7,558 once invoked, about $0.0001 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 commands, from other repositories
f5-gate
Quality gate management with evidence collection.
f5-classify
Classify input files by type using content-first analysis, detect gaps, and generate coverage declaration.
f5-implement
Implement features and fix bugs with traceability.
f5-import
Import documents - single, batch, analyze, or schema management.
f5-analytics
View project analytics and metrics.
f5-design
Generate design documents and specifications (D1-D4).