Run any Skill in Manus with one click

co-eval

Stars0

Forks0

UpdatedApril 20, 2026 at 01:07

Layer 1 session self-eval for claude-codex-orchestration. Two-axis rating (Ambition × Execution) with locked 3×3 composite matrix (score 1–5), mandatory Devil's Advocate (argue lower AND higher before committing), anti-inflation check (last 5 entries, 4+ identical flags). Persists to .eval-scores.jsonl. Run at session end or when long-session prompt triggers (≥10 dispatches OR ≥6h since last eval). Delegates to claude-codex-orchestration references/self-correction.md Layer 1.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

dy9759

dy9759/claude-codex-orchestration

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name

co-eval

description

/co-eval — Session Self-Eval (Layer 1)

Full protocol: ~/.claude/skills/claude-codex-orchestration/references/self-correction.md §Layer 1.

Quick run

Axis A — Ambition: Low / Medium / High (orchestration complexity attempted)
Axis B — Execution: Poor / Adequate / Strong (how it went)
Devil's Advocate (mandatory): argue lower → argue higher → commit to final
Lookup score in locked 3×3 composite matrix (1–5)
Anti-inflation: read last 5 .eval-scores.jsonl entries; 4+ identical → flag
Write {"date","score","ambition","execution","task","weak_point"} to .eval-scores.jsonl

Reset long-session counters:

rm -f ~/.claude/skills/claude-codex-orchestration/.last-eval-dispatch-count
rm -f ~/.claude/skills/claude-codex-orchestration/.last-eval-timestamp

If no orchestration session happened (meta case)

If the current session was building the skill (not using it), /co-eval does not apply — use /co-score instead (Layer 0 skill edit rubric).

More from this repository

same repository

claude-codex-orchestration

dy9759/claude-codex-orchestration

Use when coordinating Claude Code + Codex as dual agents with Gemini as frontend/UI specialist consultant (via gemini-cli MCP), delegating parallel implementation of bounded modules to Codex, splitting work by boundary-clarity not domain, controlling token consumption, cross-harness setup (Cursor/Codex/OpenCode), pre-task thinking (/co-think), strategic plan review (/co-plan-review), engineering principles enforcement (Hyrum, Beyoncé, Chesterton, trunk-based, shift-left, feature-flags, deprecation, maintainability harness, testing quality), UI style standard (shadcn/radix-nova), and knowledge compounding. Self-contained; optional plugins and Gemini MCP auto-detected.

2026-05-270

co-think

dy9759/claude-codex-orchestration

Pre-task thinking for claude-codex-orchestration (grill / office-hours style). Source-first: inspect repo/docs before asking. Product/Design, Technical/Approach, and Domain/Docs lanes. Ask only user-owned or genuinely ambiguous questions, one at a time, with recommendation + confidence. High-verification-risk fuzzy work becomes a Run Contract before dispatch. Always ends with Premise Challenge. Optional Codex cold-read second opinion. Delegates to references/thinking-decision.md.

2026-05-240

co-compound

dy9759/claude-codex-orchestration

Knowledge compounding for claude-codex-orchestration. Capture a solved non-trivial problem to docs/solutions/[category]/[slug]-[date].md with YAML frontmatter. Two modes: Full (4 parallel subagents — Context Analyzer / Solution Extractor / Related Docs Finder / Session Historian; overlap detection; Phase 2.5 selective refresh of older docs; discoverability check) or Lightweight (single pass). Delegates to claude-codex-orchestration references/knowledge-compounding.md.

2026-05-230

co-loop

dy9759/claude-codex-orchestration

Autonomous background refinement loop for claude-codex-orchestration. Runs /co-eval + /co-review, if candidate ≥ 6 runs /co-promote and commits, then schedules next cycle via ScheduleWakeup (270s, stays within cache TTL). Never self-stops — continues until user manually interrupts. Darwin ratchet: next session scoring the promoted dimension must improve or rule is reverted. Strategy escalation for persistent weak points (5/8/12/15+ sessions).

2026-05-230

co-plan-review

dy9759/claude-codex-orchestration

CEO-mode plan review for claude-codex-orchestration. Run after an Execution Plan is drafted. User chooses one of four modes (EXPAND/SELECTIVE/HOLD/REDUCE) dictating posture — dream bigger vs baseline+cherry-pick vs make-bulletproof vs minimum-viable. Seven Prime Directives apply in all modes: zero silent failures / named errors / shadow paths / interaction edge cases / observability-is-scope / deferred-is-written-down / security-is-scope. Critical rule: every scope change is explicit user opt-in. Delegates to references/thinking-decision.md.

2026-05-230

co-sessions

dy9759/claude-codex-orchestration

Cross-session history search for claude-codex-orchestration. Before starting complex work, dispatch a general-purpose subagent to search ~/.claude/projects/ and ~/.codex/sessions/ for prior investigations of the same problem. Returns prior approaches tried, dead ends and why they failed, key decisions + rationale, related context. Avoids repeating failed paths from past sessions. Delegates to claude-codex-orchestration references/knowledge-compounding.md.

2026-05-230

name

co-eval

description

/co-eval — Session Self-Eval (Layer 1)

Full protocol: ~/.claude/skills/claude-codex-orchestration/references/self-correction.md §Layer 1.

Quick run

Axis A — Ambition: Low / Medium / High (orchestration complexity attempted)
Axis B — Execution: Poor / Adequate / Strong (how it went)
Devil's Advocate (mandatory): argue lower → argue higher → commit to final
Lookup score in locked 3×3 composite matrix (1–5)
Anti-inflation: read last 5 .eval-scores.jsonl entries; 4+ identical → flag
Write {"date","score","ambition","execution","task","weak_point"} to .eval-scores.jsonl

Reset long-session counters:

rm -f ~/.claude/skills/claude-codex-orchestration/.last-eval-dispatch-count
rm -f ~/.claude/skills/claude-codex-orchestration/.last-eval-timestamp

If no orchestration session happened (meta case)

If the current session was building the skill (not using it), /co-eval does not apply — use /co-score instead (Layer 0 skill edit rubric).