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 ayberkcansever/ai-skills --skill tech-radargit clone --depth 1 https://github.com/ayberkcansever/ai-skillsWrote 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/ayberkcansever/ai-skills/tech-radar)<a href="https://agentmods.dev/skills/ayberkcansever/ai-skills/tech-radar"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/tech-radar/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/ayberkcansever/ai-skills/tech-radar"><img src="https://agentmods.dev/badge/skills/ayberkcansever/ai-skills/tech-radar.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 | $0.00095 | $0.01461 |
| Opus 5 | $0.00048 | $0.00731 |
| Sonnet 5 | $0.00019 | $0.00292 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
tech-radar 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 12d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Radar
Goal: answer "what should I learn next?" for a principal software + AI engineer — a Thoughtworks-style radar, not a trends listicle. Every candidate lands on one of four rings in its quadrant, and the Learn ring is the answer. Every placement must survive: "why this, why now, and why for someone at this level?"
This skill finds topics; sibling learn (~/.cursor/skills/learn/) briefs them. Shared library: briefs are this skill's memory; this skill's Learn ring is that skill's input queue.
The role lens
Apply ruthlessly. Principal software + AI engineer needs:
- Decision leverage — architecture choices, build-vs-buy, platform bets, how you review others' designs. Not "another framework that renders lists".
- AI engineering depth — agents, serving/inference economics, evals, retrieval, routing, AI-adjacent infra. Signal over demos. One strand of the lens, not the scan's default topic.
- Durability — still matters in 2 years. Hot repo, no production adoption → Watch, not Learn.
- Force-multiplier — upgrades how the team works, not personal trivia.
- 101-feasibility — correct 101 in roughly a day via the learn loop. Semester-scale → recommend the entry slice.
Out of scope: junior fundamentals, certification chasing, single-vendor launch fluff, marketing-only evidence.
A scan whose pool is nearly all AI with no AI focus filter is a skew bug. Classify every candidate into a Thoughtworks quadrant:
- Techniques — ways of working (patterns, practices, approaches).
- Platforms — things you build on (clouds, runtimes, databases, inference platforms).
- Tools — software you use rather than build on.
- Languages & Frameworks — languages, major framework releases, SDKs, stdlib.
Rings (learning verbs, not Thoughtworks Adopt/Trial/Assess/Hold):
- Learn — start now. Production-grade; would start
/learnthis week. Selective; past ~8 you are not choosing. - Try — cheap pass is enough (release notes / half-day skim), or second in queue.
- Watch — real signal, not rankable yet. Every Watch blip has a concrete promote when:.
- Skip — deliberately not spending time, plus what would move it back in.
What ships with it
8 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.
- 12d ago First seen · 103 lines · 95 tokens per session scan A f7a5b0ab3d6e
tech-radar is a skill published in the GitHub repository ayberkcansever/ai-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 95 tokens to every session and 1,461 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
toolport
Use when the user asks for any external action or data: email, payments, deployments, databases, repos, issues, files, web search, messaging, or any connected service. Toolport is the front door to every MCP server on this machine; search it before concluding a capability is unavailable.
explain
Guided code tour of a file or subsystem this session touched — entry point, the load-bearing pieces, the edges, and what connects to it.
digest
Generate a structured vibe-learn learning digest of the current coding session from .vibe-learn/session-log.jsonl.
learn
Explain recent vibe-learn session activity or answer a question about what was built, grounded in .vibe-learn/session-log.jsonl.
quiz
Check your understanding of the vibe-learn session — recall questions grounded in the session log, with results tracked across sessions in the knowledge ledger.
lookup-topic
Look up a help topic with progressive depth. First call returns concept, repeat calls escalate to task then reference. Triggers on: look up topic, open template, tell me more, go deeper, start over.