A
Anthropic-Cybersecurity-Skills
81.5
36,292 stars · Apache-2.0
AI Agents
deepseek-harness leads by 15.9 · decisive
A
81.5
36,292 stars · Apache-2.0
B · leads
97.4
282,805 stars · MIT
Anthropic-Cybersecurity-Skills versus deepseek-harness is a AI Agents comparison assembled from public repository metrics, the license on file, and whether each product can be self-hosted. Anthropic-Cybersecurity-Skills is written mainly in Python; deepseek-harness is written mainly in TypeScript. The composite score is 81.5 for Anthropic-Cybersecurity-Skills and 97.4 for deepseek-harness.
deepseek-harness has 282,805 GitHub stars to Anthropic-Cybersecurity-Skills's 36,292, a gap of 246,513 (7.79×). Forks are 4,439 for Anthropic-Cybersecurity-Skills and 35,041 for deepseek-harness. On the log scale used inside this pair, adoption is 84 versus 100, and the fork community is 80 versus 100.
Push history: Anthropic-Cybersecurity-Skills was last pushed on 31 August 2026 (78 days ago), and deepseek-harness was last pushed on 13 November 2026 (4 days ago). Open issues stand at 70 for Anthropic-Cybersecurity-Skills (0.002 per star) and 0 for deepseek-harness (0.000 per star). Issue-health scores are 96 and 96; activity scores are 58 and 92.
Anthropic-Cybersecurity-Skills is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. deepseek-harness is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. License scores in this pair are 96 for Anthropic-Cybersecurity-Skills and 96 for deepseek-harness. This is a procurement signal, not legal advice.
In AI Agents, both Anthropic-Cybersecurity-Skills (36,292 stars) and deepseek-harness (282,805 stars) are marked self-hostable. Deploy scores are 100 and 100. Running either one means you own upgrades, backups, and the license duties that follow a modified copy. Pricing labels on file: Anthropic-Cybersecurity-Skills is open source, deepseek-harness is open source.
deepseek-harness is ahead on every scored dimension that is not level. Level dimensions: issue health, license flexibility, self-hosting. The widest gap is recent activity at 34 points (58 vs 92), and the tightest is self-hosting at 0 points (100 vs 100).
deepseek-harness finishes ahead at 97.4 against Anthropic-Cybersecurity-Skills at 81.5, a 15.9 point decisive margin under the published weights.
Scores are computed inside this pair only. Method and weights.
Bars are scaled within the row. Higher is stronger. Open issues are a raw count, so that row has no bar.
| Signal | Anthropic-Cybersecurity-Skills | deepseek-harness |
|---|---|---|
| GitHub stars | 36,292 | 282,805 |
| Forks | 4,439 | 35,041 |
| Open issues | 70 | 0 |
| Adoption | 84 | 100 |
| Activity | 58 | 92 |
| Community | 80 | 100 |
| Issue health | 96 | 96 |
| License | 96 | 96 |
| Self-hosting | 100 | 100 |
| Composite | 81.5 | 97.4 |
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0
DeepSeek Harness: Everything is a Plugin.
deepseek-harness has more GitHub stars: 282,805 versus 36,292 for Anthropic-Cybersecurity-Skills. The gap is 246,513 stars.
deepseek-harness was pushed more recently: 13 November 2026 versus 31 August 2026 for Anthropic-Cybersecurity-Skills. That is 74 days apart.
Yes. This catalog marks both Anthropic-Cybersecurity-Skills and deepseek-harness as self-hostable. Confirm each project's deploy docs before you plan a migration.
Anthropic-Cybersecurity-Skills is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. deepseek-harness is listed as MIT, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. Read both grants before you embed either codebase in a hosted product. This is not legal advice.
deepseek-harness scores 97.4 and Anthropic-Cybersecurity-Skills scores 81.5. This page calls that a decisive lead for deepseek-harness.