architecture
Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate…
@kanevryInstall SkillDevelopment
Skill
/harness-audit
Run the harness audit and report the rubric score for this repository
Claude Code
$ npx -y skills add Kanevry/session-orchestrator --skill harness-audit --agent claude-code
Codex
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a codex -y
Cursor
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a cursor -y
Gemini CLI
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a gemini-cli -y
GitHub Copilot
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a github-copilot -y
OpenCode
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a opencode -y
Windsurf
$ npx skills add Kanevry/session-orchestrator --skill harness-audit -a windsurf -y
SKILL.md
harness-audit.SKILL.mdname: harness-audit description: Run the harness audit and report the rubric score for this repository user-invocable: true model: inherit
Harness Audit
Invocation
`/harness-audit` takes no arguments — `$ARGUMENTS` is always ignored; anything passed is discarded without a warning. Run the audit exactly as described below and report the rubric score.
The user wants to audit this repository against the session-orchestrator harness rubric. There are no arguments.
Run the audit script and surface the results:
node scripts/harness-audit.mjs
The script writes a concise human-readable summary to stderr and emits a JSON record to stdout. Capture both:
1. Print the stderr summary verbatim so the user sees it immediately. 2. Parse the stdout JSON and report:
- `summary.overall_band` — `healthy`, `warn`, or `critical`
- `summary.overall_mean_0_10` — the numeric score
- Any category with `score_0_10 < 7`, listing its name and score
The full JSON record is also appended automatically to `.orchestrator/metrics/audit.jsonl` by the script — no additional action needed.
If the script exits non-zero, report the error output to the user verbatim. Do not interpret or retry.
Stats
53
Stars
6
Forks
Active
Maintenance
JavaScript
Language
MIT
License
Last commit
Created
Ships withsession-orchestrator
Your coding agents get an agreed plan, a check after each round of changes and a handover to the next session. A free, MIT-licensed workflow plugin for people running Claude Code, Codex CLI, Cursor IDE or Pi on a git repository.
5252 skills14 agents1 MCP
Stars on GitHub
Momentum
- stars in total
- 52
Other skills on session-orchestrator.
@kanevryInstall Skillautopilot
Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor →…
@kanevryInstall Skillbootstrap
Use this skill when scaffolding the minimum repository structure required by session-orchestrator. Invoked automatically by the…
@kanevryInstall Skillbrainstorm
Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ…
@kanevryInstall Skillclaude-md-drift-check
Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Ten…
@kanevryInstall SkillMore skills from other plugins.
Auto-invoked
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
@obraInstall Skillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
@mattpocockInstall SkillAuto-invoked
Questions about harness-audit.
- Which coding agents can use harness-audit?
- harness-audit installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.