DenisSergeevitch/agents-best-practices
Frameworks & Eval · tested 2026-09-22 · by the Hlido desk, not the vendor
In short: A well-adopted, provider-neutral agent-skill and harness-design guide — reference material, not a runnable product.
8 PASS · 2 FAIL of 10 public-surface claims
Visit DenisSergeevitch/agents-best-practices → scorecard.json
Quick answer
DenisSergeevitch/agents-best-practices scores 82/100 (STEADY) on Hlido’s independent, hands-on test (reviewed 2026-09-22). STEADY (82), the repo-surface ceiling: reachable, MIT-licensed, documented install/usage, 2.1K stars, recent commits, and a CLI/agent-skill consumption path. Pricing: Open source (free entry point documented).
agents-best-practices is a provider-neutral agent skill and best-practices guide for building agentic harnesses across Codex, Claude Code and similar tools. It is reference/skill content rather than an executable service, and on that footing it does well: 2.1K stars is strong adoption for a guide, it is MIT-licensed, the README documents how to consume it, and it is actively maintained. It was previously miscategorized as Image & Design; it is squarely Frameworks & Eval. The right expectation to set is that its value is the quality of the guidance it encodes — which repo signals cannot grade — while the 82 reflects that it is a healthy, permissively-licensed, well-adopted, agent-consumable repository.
Why STEADY
STEADY (82), the repo-surface ceiling: reachable, MIT-licensed, documented install/usage, 2.1K stars, recent commits, and a CLI/agent-skill consumption path. Not VITAL because the substance — whether the best practices actually improve agent outcomes — needs hands-on evaluation the repo signals cannot provide, and there are no releases or CI to point to.
Public-surface checklist
- PASS Repo reachable (required) — GH API 200 for DenisSergeevitch/agents-best-practices
- PASS Readme present (required) — README length 13451
- PASS License present (required) — MIT
- PASS Install documented (required) — install/usage section found in README
- PASS Active 12mo (required) — last push 17d ago
- FAIL Releases present — no releases
- PASS Community traction — 2124 stars
- FAIL Ci or tests — no .github/workflows
- PASS Recent commit 90d — last push 17d ago
- PASS Agent consumable — CLI install line in README
What we saw
1 screenshot captured by the Hlido engine during the reviewed run (run-10423b9a11f93bd6-github-com). Our own captures — not vendor marketing material.
What it does well
- Strong adoption for a guide/skill repo (2.1K stars)
- Provider-neutral — targets Codex, Claude Code and general agentic harnesses
- MIT-licensed with a documented consumption path
- Actively maintained (commits ~17 days before review)
What it fails at
- Not a runnable product — it is reference/skill content
- No releases and no CI workflows
- The quality/impact of the guidance itself was not evaluated
Best for
- Engineers designing agent harnesses who want a provider-neutral starting point
- Teams standardizing agent-skill conventions across Codex/Claude Code
Not recommended for
- Buyers looking for an executable agent or service
- Anyone needing benchmarked evidence that the practices improve outcomes
Pricing & access
- ModelOpen source
- Free entry pointYes — a free tier or open-source edition is documented
Derived from Hlido-held evidence only (engine checklist + editorial text); quotes are verbatim from the scorecard; not vendor-supplied; re-derived daily. Verify current prices on the vendor's pricing page. Last verified 2026-07-16.
Related agents
Agent relevance
CLI
Agentic-Commerce Readiness 28/100 · SURFACE-ONLY
Independent readiness for agent delegation & transaction. How it’s scored · check live
Consumed as an agent skill / best-practices pack rather than a running service; installable into agent harnesses (Codex, Claude Code). Value is guidance, not a callable interface.
Agent-friendly score: 5/10
Score over time
The longitudinal record — every point is the score as published on that date. Raw series.
Evidence
scorecard.json · transparency passport · registry · methodology
Embed this trust badge
Markdown
[](https://hlido.eu/check/?agent=denissergeevitch-agents-best-practices)HTML
<a href="https://hlido.eu/check/?agent=denissergeevitch-agents-best-practices"><img src="https://hlido.eu/badge/denissergeevitch-agents-best-practices.svg" alt="Hlido trust score"></a>