Sensez – helping coding agents catch their own code smells is a skill AI agent for To identify and fix potential code smell issues in AI-generated code prior to deployment. Pricing: Free + usage-based tiers. As of 2026-10-27, KanonAgent records 2 upvotes. First indexed by KanonAgent on 2026-09-02.
Sensez enables AI coding agents to automatically detect and correct their own code quality issues before submission.
2 upvotes
Tracked by Kanon since Sep 2, 2026
Status basis: npm_downloads_7d momentum fell to -3 per 3d from 190 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -3 per 3d from 190 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 190 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 207 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 190 in the last 3d vs 17 in the 3d before (ratio 11.2x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 190 in the last 3d vs 17 in the 3d before (ratio 11.2x, threshold 1.5x)
- Accelerating npm_downloads_7d gained 17 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 17 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 17 in the last 3d vs 11 in the 3d before (ratio 1.5x, threshold 1.5x)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 18 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 18 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 17 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 8 per 3d from 49 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 3 per 3d from 223 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 17 per 3d from 208 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to 49 per 3d from 168 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 223 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 54 per 3d from 169 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 208 in the last 3d vs 9 in the 3d before (ratio 23.1x, threshold 1.5x)
- Anomaly daily change 169.0 is 7.8 standard deviations from this entity's own prior mean (-10.5±23.0, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 168 in the last 3d vs 9 in the 3d before (ratio 18.7x, threshold 1.5x)
- Anomaly daily change 169.0 is 7.8 standard deviations from this entity's own prior mean (-10.5±23.0, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -66 per 3d from 76 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -68 per 3d from 78 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -61 per 3d from 87 (<= 40% of the prior window)
🔎 Known / Unknown
11 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | inferred | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | 2 | inferred | 1 quote(s) |
| Pricing model | — | unknown | — |
| Integrations | mcp | inferred | 1 quote(s) |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · skill
Job to be doneTo identify and fix potential code smell issues in AI-generated code prior to deployment.
AutonomyL2 · tool-calling(evidence: "uv run sensez noze . # scan once — no install needed wi…")
Who it is forAI programming developers and AI engineering teams.
Prerequisitesopen source · self-hostable
Integrationsmcp
PricingFree + usage-based tiers
Traction · why it is risingAttracting early adopters in AI development circles who are pushing for self-correcting, production-ready AI agents.
Why it matters
It introduces a critical layer of self-awareness and quality control in AI coding agents, advancing the maturity of autonomous development workflows.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“uv add --dev sensez # or install globally: uv tool install sensez”— readme
“uv run sensez noze . # scan once — no install needed wi”— readme
“registers the MCP server”— readme
“It runs inside the coding-agent loop”— readme
“registers Sensez as an MCP server with your coding agent — Claude Code, Cursor, Cline, Codex, OpenCode, and Pi are supported.”— readme
Signal source: Show HN
Visit official site →
📛 Official badgefor your site / README
Building Sensez? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is Sensez?
Sensez enables AI coding agents to automatically detect and correct their own code quality issues before submission.
What does Sensez do?
To identify and fix potential code smell issues in AI-generated code prior to deployment.
Why does Sensez matter?
It introduces a critical layer of self-awareness and quality control in AI coding agents, advancing the maturity of autonomous development workflows.
How much does Sensez cost?
Free + usage-based tiers
Is Sensez free?
Yes — Sensez has a free tier. Pricing as stated on its own page: Free + usage-based tiers
Is Sensez open source?
Yes — Sensez is open source.
Can I self-host Sensez?
Yes — Sensez can be self-hosted.
What does Sensez integrate with?
mcp
How popular is Sensez?
As tracked by KanonAgent: 2 upvotes (first indexed 2026-09-02).
What are the best Sensez alternatives?
Similar AI agents tracked by KanonAgent: Stealth Venture, taste-skill, archify, open-design, deer-flow, ruflo.