open-coder-ai/context-report

docs: explain what each measured attribute actually means 14 days ago

good first issue

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

measure: extend the instruction sample 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

measure: extend the catalog sample beyond three marketplaces 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

measure: produce a report for a plugin you actually use 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

providers: add a vertex backend 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

providers: add a bedrock backend 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

providers: add a gemini backend 14 days ago

help wanted good first issue

open-coder-ai/context-report

0

An open, signed report format for whether an agent plugin, hook, skill, or AGENTS.md actually works.

Python

#agent-plugins#agents-md-template#ai-agents#attestation#benchmarking#claude-code#claude-skills#codex-cli#cursor-ide#efficacy#github-copilot#hooks#in-toto#llm-evaluation#mcp#model-context-protocol#plugin-catalog#provenance#sigstore#supply-chain-security

Open Issues Need Help