wip: [01-stabilize] paused at task 1/1 - OCR Hallucination Immune logic via Semantic delta window and fret-isolation

.agent/knowledge/everything_claude/.codex/AGENTS.md

@@ -0,0 +1,93 @@
+# ECC for Codex CLI
+
+This supplements the root `AGENTS.md` with Codex-specific guidance.
+
+## Model Recommendations
+
+| Task Type | Recommended Model |
+|-----------|------------------|
+| Routine coding, tests, formatting | GPT 5.4 |
+| Complex features, architecture | GPT 5.4 |
+| Debugging, refactoring | GPT 5.4 |
+| Security review | GPT 5.4 |
+
+## Skills Discovery
+
+Skills are auto-loaded from `.agents/skills/`. Each skill contains:
+- `SKILL.md` — Detailed instructions and workflow
+- `agents/openai.yaml` — Codex interface metadata
+
+Available skills:
+- tdd-workflow — Test-driven development with 80%+ coverage
+- security-review — Comprehensive security checklist
+- coding-standards — Universal coding standards
+- frontend-patterns — React/Next.js patterns
+- frontend-slides — Viewport-safe HTML presentations and PPTX-to-web conversion
+- article-writing — Long-form writing from notes and voice references
+- content-engine — Platform-native social content and repurposing
+- market-research — Source-attributed market and competitor research
+- investor-materials — Decks, memos, models, and one-pagers
+- investor-outreach — Personalized investor outreach and follow-ups
+- backend-patterns — API design, database, caching
+- e2e-testing — Playwright E2E tests
+- eval-harness — Eval-driven development
+- strategic-compact — Context management
+- api-design — REST API design patterns
+- verification-loop — Build, test, lint, typecheck, security
+- deep-research — Multi-source research with firecrawl and exa MCPs
+- exa-search — Neural search via Exa MCP for web, code, and companies
+- claude-api — Anthropic Claude API patterns and SDKs
+- x-api — X/Twitter API integration for posting, threads, and analytics
+- crosspost — Multi-platform content distribution
+- fal-ai-media — AI image/video/audio generation via fal.ai
+- dmux-workflows — Multi-agent orchestration with dmux
+
+## MCP Servers
+
+Treat the project-local `.codex/config.toml` as the default Codex baseline for ECC. The current ECC baseline enables GitHub, Context7, Exa, Memory, Playwright, and Sequential Thinking; add heavier extras in `~/.codex/config.toml` only when a task actually needs them.
+
+### Automatic config.toml merging
+
+The sync script (`scripts/sync-ecc-to-codex.sh`) uses a Node-based TOML parser to safely merge ECC MCP servers into `~/.codex/config.toml`:
+
+- **Add-only by default** — missing ECC servers are appended; existing servers are never modified or removed.
+- **7 managed servers** — Supabase, Playwright, Context7, Exa, GitHub, Memory, Sequential Thinking.
+- **Package-manager aware** — uses the project's configured package manager (npm/pnpm/yarn/bun) instead of hardcoding `pnpm`.
+- **Drift warnings** — if an existing server's config differs from the ECC recommendation, the script logs a warning.
+- **`--update-mcp`** — explicitly replaces all ECC-managed servers with the latest recommended config (safely removes subtables like `[mcp_servers.supabase.env]`).
+- **User config is always preserved** — custom servers, args, env vars, and credentials outside ECC-managed sections are never touched.
+
+## Multi-Agent Support
+
+Codex now supports multi-agent workflows behind the experimental `features.multi_agent` flag.
+
+- Enable it in `.codex/config.toml` with `[features] multi_agent = true`
+- Define project-local roles under `[agents.<name>]`
+- Point each role at a TOML layer under `.codex/agents/`
+- Use `/agent` inside Codex CLI to inspect and steer child agents
+
+Sample role configs in this repo:
+- `.codex/agents/explorer.toml` — read-only evidence gathering
+- `.codex/agents/reviewer.toml` — correctness/security review
+- `.codex/agents/docs-researcher.toml` — API and release-note verification
+
+## Key Differences from Claude Code
+
+| Feature | Claude Code | Codex CLI |
+|---------|------------|-----------|
+| Hooks | 8+ event types | Not yet supported |
+| Context file | CLAUDE.md + AGENTS.md | AGENTS.md only |
+| Skills | Skills loaded via plugin | `.agents/skills/` directory |
+| Commands | `/slash` commands | Instruction-based |
+| Agents | Subagent Task tool | Multi-agent via `/agent` and `[agents.<name>]` roles |
+| Security | Hook-based enforcement | Instruction + sandbox |
+| MCP | Full support | Supported via `config.toml` and `codex mcp add` |
+
+## Security Without Hooks
+
+Since Codex lacks hooks, security enforcement is instruction-based:
+1. Always validate inputs at system boundaries
+2. Never hardcode secrets — use environment variables
+3. Run `npm audit` / `pip audit` before committing
+4. Review `git diff` before every push
+5. Use `sandbox_mode = "workspace-write"` in config

.agent/knowledge/everything_claude/.codex/agents/docs-researcher.toml

@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Verify APIs, framework behavior, and release-note claims against primary documentation before changes land.
+Cite the exact docs or file paths that support each claim.
+Do not invent undocumented behavior.
+"""

.agent/knowledge/everything_claude/.codex/agents/explorer.toml

@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Stay in exploration mode.
+Trace the real execution path, cite files and symbols, and avoid proposing fixes unless the parent agent asks for them.
+Prefer targeted search and file reads over broad scans.
+"""

.agent/knowledge/everything_claude/.codex/agents/reviewer.toml

@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "high"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Review like an owner.
+Prioritize correctness, security, behavioral regressions, and missing tests.
+Lead with concrete findings and avoid style-only feedback unless it hides a real bug.
+"""

.agent/knowledge/everything_claude/.codex/config.toml

@@ -0,0 +1,107 @@
+#:schema https://developers.openai.com/codex/config-schema.json
+
+# Everything Claude Code (ECC) — Codex Reference Configuration
+#
+# Copy this file to ~/.codex/config.toml for global defaults, or keep it in
+# the project root as .codex/config.toml for project-local settings.
+#
+# Official docs:
+# - https://developers.openai.com/codex/config-reference
+# - https://developers.openai.com/codex/multi-agent
+
+# Model selection
+# Leave `model` and `model_provider` unset so Codex CLI uses its current
+# built-in defaults. Uncomment and pin them only if you intentionally want
+# repo-local or global model overrides.
+
+# Top-level runtime settings (current Codex schema)
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+web_search = "live"
+
+# External notifications receive a JSON payload on stdin.
+notify = [
+  "terminal-notifier",
+  "-title", "Codex ECC",
+  "-message", "Task completed!",
+  "-sound", "default",
+]
+
+# Prefer AGENTS.md and project-local .codex/AGENTS.md for instructions.
+# model_instructions_file replaces built-in instructions instead of AGENTS.md,
+# so leave it unset unless you intentionally want a single override file.
+# model_instructions_file = "/absolute/path/to/instructions.md"
+
+# MCP servers
+# Keep the default project set lean. API-backed servers inherit credentials from
+# the launching environment or can be supplied by a user-level ~/.codex/config.toml.
+[mcp_servers.github]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-github"]
+
+[mcp_servers.context7]
+command = "npx"
+args = ["-y", "@upstash/context7-mcp@latest"]
+
+[mcp_servers.exa]
+url = "https://mcp.exa.ai/mcp"
+
+[mcp_servers.memory]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-memory"]
+
+[mcp_servers.playwright]
+command = "npx"
+args = ["-y", "@playwright/mcp@latest", "--extension"]
+
+[mcp_servers.sequential-thinking]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+
+# Additional MCP servers (uncomment as needed):
+# [mcp_servers.supabase]
+# command = "npx"
+# args = ["-y", "supabase-mcp-server@latest", "--read-only"]
+#
+# [mcp_servers.firecrawl]
+# command = "npx"
+# args = ["-y", "firecrawl-mcp"]
+#
+# [mcp_servers.fal-ai]
+# command = "npx"
+# args = ["-y", "fal-ai-mcp-server"]
+#
+# [mcp_servers.cloudflare]
+# command = "npx"
+# args = ["-y", "@cloudflare/mcp-server-cloudflare"]
+
+[features]
+# Codex multi-agent support is experimental as of March 2026.
+multi_agent = true
+
+# Profiles — switch with `codex -p <name>`
+[profiles.strict]
+approval_policy = "on-request"
+sandbox_mode = "read-only"
+web_search = "cached"
+
+[profiles.yolo]
+approval_policy = "never"
+sandbox_mode = "workspace-write"
+web_search = "live"
+
+[agents]
+max_threads = 6
+max_depth = 1
+
+[agents.explorer]
+description = "Read-only codebase explorer for gathering evidence before changes are proposed."
+config_file = "agents/explorer.toml"
+
+[agents.reviewer]
+description = "PR reviewer focused on correctness, security, and missing tests."
+config_file = "agents/reviewer.toml"
+
+[agents.docs_researcher]
+description = "Documentation specialist that verifies APIs, framework behavior, and release notes."
+config_file = "agents/docs-researcher.toml"