manhua-man/harness-coding-protocol
Plugin Claude Code
Plugin marketplace listing 1 plugin: harness-coding-protocol.
5 yesterday A
tokens not measured
original MIT
manhua-man/harness-coding-protocol
Plugin Claude Code
AI-driven harness protocol plugin — IDE /harness-init for agent-native grounding, root-truth generation, and confirmed apply.
5 yesterday A
tokens not measured
original MIT
harness-init
03manhua-man/harness-coding-protocol
Command
Bootstrap a target repo via /harness-init — ground, read, judge, confirm, apply. The IDEAgent itself reads, judges, and writes the root-truth files after one confirmation.
5 yesterday A 40 tokens
original MIT
manhua-man/harness-coding-protocol
Command
Full audit of AI entry docs (AGENTS, CLAUDE, steering, Cursor rules) with quality report before any edits. Use for periodic health checks or after large refactors.
5 yesterday A 37 tokens
original MIT
manhua-man/harness-coding-protocol
Command
Write session learnings back into AI entry docs (AGENTS.md, CLAUDE.md, steering). Lightweight incremental companion to /project-ai-docs-steward.
5 yesterday A 34 tokens
original MIT
update-docs
06manhua-man/harness-coding-protocol
Command
Sync human documentation with implementation reality: $ARGUMENTS.
5 yesterday A 1 tokens
original MIT
manhua-man/harness-coding-protocol
Skill Claude CodeCodex
Audit and converge a repository's human documentation using the governance model proven in practice: single source of truth, lifecycle-tiered docs (current truth / lessons / validation), project content kept out of pipeline docs, dead docs deleted instead of archived, and honest evidence labels. Use when docs feel…
5 yesterday B 85 tokens
original MIT
harness-init
08manhua-man/harness-coding-protocol
Skill Claude CodeCodex
Bootstrap a target repo via /harness-init — ground, read, judge, confirm, apply. The IDEAgent itself reads, judges, and writes the root-truth files after one confirmation, without requiring Node/npm/npx/tsx.
5 yesterday A 53 tokens
original MIT
manhua-man/harness-coding-protocol
Skill Claude CodeCodex
Audit and improve media or AI-generation pipelines whose command may succeed while the delivered output is unusable. Use direct output evidence, attempt automatic repair/retry/fallback, quarantine bad attempts for diagnosis, and stop only when no valid deliverable can be produced.
5 yesterday A 56 tokens
original MIT
manhua-man/harness-coding-protocol
Skill Claude CodeCodex
Audit and improve a target repo's AI entry documentation (AGENTS.md, CLAUDE.md, steering, .cursor rules). Use after /harness-init or when AI context drifts. Generic harness protocol skill — parameterize paths to the open workspace.
5 yesterday A 60 tokens
original MIT