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 rjmurillo/ai-agents --skill programming-advisorgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/programming-advisor)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/programming-advisor"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/programming-advisor/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/rjmurillo/ai-agents/programming-advisor"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/programming-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00113 | $0.04060 |
| Opus 5.5 | $0.00045 | $0.01624 |
| Sonnet 5.5 | $0.00023 | $0.00812 |
| Haiku 4.5 | $0.00011 | $0.00406 |
Grade A, and why
programming-advisor 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 — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Programming Advisor - "Reinventing the Wheel" Detector
Triggers
| Trigger Phrase | Action |
|---|---|
| "should I build X or use a library" | Search internal prior-art first (Step 2a), then external solutions, provide comparison |
| "find existing solutions for X" | Search internal prior-art first (Step 2a), then web search, categorize findings |
| "is there a package for X" | Check existing dependencies first (Step 2a), then search npm/pip/cargo/etc |
| "build vs buy for X" | Tactical: generate cost comparison table; Strategic (>$50K, multi-year, partner/defer options): delegate to buy-vs-build-framework |
| "check if X exists before building" | Run full wheel detection workflow |
| "do we already have X" / "is there existing code for X in this repo" | Search internal prior-art first (leverage/extend), then external |
When to use / Do NOT use
Use this skill: "is there a library for parsing YAML in Python", "do we already have a retry helper in this repo", "find an existing solution before writing a new rate limiter". Every one of these names one narrow, tactical, immediately buildable thing.
Do NOT use this skill for: "should we build or buy a customer data platform,
partner with a vendor, or defer the investment for two years" (strategic,
multi-year, multi-option; use buy-vs-build-framework instead). The dividing
line is time horizon and option count: one tactical answer stays here, a
multi-option strategic trade-off with TCO goes to buy-vs-build-framework.
Core Philosophy
Before writing a single line of code, determine if the wheel already exists. Vibe coding burns tokens, time, and creates maintenance burden. Existing solutions often provide better quality, security patches, and community support.
Process
Step 1: Capture Intent
Extract from user request:
- What: Core functionality needed
- Why: Use case / problem being solved
- Constraints: Language, platform, budget, licensing requirements
Step 2: Search for Existing Solutions
What ships with it
6 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.
- 1mo ago Changed · +29 lines 8bc90b73f388
- 1mo ago Changed · +2 lines b2565bf7871b
- 1mo ago Changed 3e0b270d9f8c
- 1mo ago First seen · 391 lines · 113 tokens per session scan A c921fd24a13d
programming-advisor is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 113 tokens to every session and 4,060 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 2026-09-03.
Other skills, from other repositories
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
review-remote
Review open PR/MR and publish findings.
phoenix-review
Review completed work against the Intent Contract's acceptance criteria using objective evidence, not opinion — re-run every check, confirm no regressions, inspect the tamper-evident trace, and surface only real issues (bugs, unmet criteria, regressions). Use before shipping, after a feature is built, or when the user…
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.