### Start LiteLLM Proxy Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/provider-bridge.md Start the LiteLLM proxy server with a specified configuration file, host, and port. ```bash litellm --config litellm-fable5.yaml --host 127.0.0.1 --port 4000 ``` -------------------------------- ### Install FableCodex Plugin Source: https://github.com/baskduf/fablecodex/blob/main/README.md Install the stable release of the FableCodex plugin and add the fable5 skill. Restart Codex after installation. ```bash codex plugin marketplace add baskduf/FableCodex --ref v0.4.1 codex plugin add codex-fable5@fablecodex ``` -------------------------------- ### Install FableCodex from Local Development Source: https://github.com/baskduf/fablecodex/blob/main/README.md Install FableCodex from a local directory, useful for development, and add the fable5 plugin. ```bash codex plugin marketplace add ~/Desktop/FableCodex codex plugin add codex-fable5@fablecodex ``` -------------------------------- ### Install LiteLLM Proxy Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/provider-bridge.md Install the LiteLLM proxy package with support for OpenAI-compatible APIs. ```bash python3 -m pip install "litellm[proxy]" ``` -------------------------------- ### Install FableCodex Development Version Source: https://github.com/baskduf/fablecodex/blob/main/README.md Install the development version of FableCodex from the main branch, along with the fable5 plugin. ```bash codex plugin marketplace add baskduf/FableCodex --ref main codex plugin add codex-fable5@fablecodex ``` -------------------------------- ### Generate LiteLLM Config Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/provider-bridge.md Generate a starter LiteLLM configuration file for a Fable-compatible model. ```bash python3 plugins/codex-fable5/skills/codex-fable5/scripts/make_litellm_config.py \ --model claude-fable-5 \ --alias claude-fable-5 \ --output litellm-fable5.yaml ``` -------------------------------- ### Implementation with Limits Command Source: https://github.com/baskduf/fablecodex/blob/main/README.md Use this command to implement fixes while adhering to specific constraints, such as not committing, pushing, or deleting branches. It also includes running unit tests and reporting residual risk. ```text @codex-fable5 Implement the fix. Do not commit, push, or delete branches. Run unit tests and report any residual risk. ``` -------------------------------- ### Create and Manage Goals with Codex Fable5 Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/task-routing.md Use this command to create a new goal with multiple steps and manage the workflow. It requires specifying a brief description, individual goals, and allows for checkpointing progress with evidence. ```bash codex-fable5 goals create --brief "Add CSV import" \ --goal "inspect::Find current import flow and tests" \ --goal "implement::Add CSV parser and UI path" \ --goal "verify::Run tests and a sample import" codex-fable5 goals next codex-fable5 goals checkpoint --id G001 --status complete --evidence "Read importer.ts and import.test.ts" codex-fable5 goals next ``` -------------------------------- ### Create New Goal Ledger Source: https://github.com/baskduf/fablecodex/blob/main/README.md Creates a new goal ledger with a brief description and multiple specific goals. Use 'codex-fable5 goals next' to proceed to the next goal. ```bash codex-fable5 goals create --brief "Migration" \ --goal "inspect::Find current behavior and tests" \ --goal "change::Implement the migration" \ --goal "verify::Run tests and inspect output" ``` ```bash codex-fable5 goals next ``` -------------------------------- ### Run Unit Tests Source: https://github.com/baskduf/fablecodex/blob/main/CONTRIBUTING.md Execute all unit tests within the 'tests' directory using Python's unittest module. ```bash python -m unittest discover -s tests -v ``` -------------------------------- ### Run Local Verification Commands Source: https://github.com/baskduf/fablecodex/blob/main/docs/RELEASING.md Execute unit tests and compile Python scripts to verify local changes before release. This includes running unittest discover, py_compile for specified scripts, and shell script checks. ```bash python3 -m unittest discover -s tests -v python3 -m py_compile \ plugins/codex-fable5/skills/codex-fable5/scripts/codex_findings.py \ plugins/codex-fable5/skills/codex-fable5/scripts/codex_goals.py \ plugins/codex-fable5/skills/codex-fable5/scripts/fable_coverage.py \ plugins/codex-fable5/skills/codex-fable5/scripts/make_litellm_config.py \ tests/test_scripts.py sh -n plugins/codex-fable5/bin/codex-fable5 sh -n plugins/codex-fable5/bin/codex-findings sh -n plugins/codex-fable5/bin/codex-goals python3 plugins/codex-fable5/skills/codex-fable5/scripts/fable_coverage.py ``` -------------------------------- ### Run Stdlib-Only Test Suite Source: https://github.com/baskduf/fablecodex/blob/main/README.md Execute the standard library tests for FableCodex. This command is used to verify the core functionality of the library. ```bash python3 -m unittest discover -s tests -v ``` -------------------------------- ### Add a New Finding Source: https://github.com/baskduf/fablecodex/blob/main/README.md Use this command to record a new review finding. Provide details such as title, severity, source, location, and evidence. ```bash codex-fable5 findings add \ --title "Missing final verification" \ --severity high \ --source review \ --location "plugins/codex-fable5/skills/codex-fable5/scripts/codex_goals.py:180" \ --evidence "Final checkpoint can complete without proof that tests ran." ``` -------------------------------- ### Tag and Push Release Source: https://github.com/baskduf/fablecodex/blob/main/docs/RELEASING.md Tag the release with the plugin version and push the tags to the origin. This is a crucial step for version control and release management. ```bash git tag v0.3.1 git push origin main --tags ``` -------------------------------- ### Add, Resolve, and Gate Findings with Codex Fable5 Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/task-routing.md Demonstrates the workflow for adding new findings, resolving existing ones with verification steps, and gating the project before finalization. Ensure the 'plugins/codex-fable5/bin' directory is in your PATH. ```bash codex-fable5 findings add \ --title "Final checkpoint can pass with unresolved review issues" \ --severity high \ --source subagent \ --evidence "Review found that the final gate only checks tests, not accepted findings." ``` ```bash codex-fable5 findings next ``` ```bash codex-fable5 findings resolve \ --id F001 \ --evidence "Added a findings gate before final checkpoint." \ --verify-cmd "python3 -m unittest discover -s tests -v" \ --verify-evidence "all tests passed" ``` ```bash codex-fable5 findings gate ``` -------------------------------- ### Run Codex Fable5 Status Helper Source: https://github.com/baskduf/fablecodex/blob/main/README.md Execute the status helper script directly from its path without modifying the system's PATH environment variable. ```bash plugins/codex-fable5/bin/codex-fable5 status ``` -------------------------------- ### Checkpoint Goal with Evidence Source: https://github.com/baskduf/fablecodex/blob/main/README.md Records a completed goal with its status and evidence. This is used for tracking progress within the goal ledger. ```bash codex-fable5 goals checkpoint \ --id G001 \ --status complete \ --evidence "Read importer.ts and import.test.ts; current parser rejects quoted commas." ``` -------------------------------- ### Set PATH for FableCodex Bin Source: https://github.com/baskduf/fablecodex/blob/main/README.md Exports the FableCodex binary directory to the system's PATH environment variable, making its commands accessible. ```bash export PATH="$PWD/plugins/codex-fable5/bin:$PATH" ``` -------------------------------- ### Execute Coverage Script Source: https://github.com/baskduf/fablecodex/blob/main/CONTRIBUTING.md Run the Fable coverage script located in the plugins directory. ```bash python plugins/codex-fable5/skills/codex-fable5/scripts/fable_coverage.py ``` -------------------------------- ### Run the Findings Gate Source: https://github.com/baskduf/fablecodex/blob/main/README.md Execute the findings gate to check for any remaining open or blocked findings before final project completion. The gate fails if blocking findings exist. ```bash codex-fable5 findings gate ``` -------------------------------- ### Debugging Command Source: https://github.com/baskduf/fablecodex/blob/main/README.md This command is used for debugging failures. It involves reproducing the issue, maintaining multiple hypotheses, gathering disconfirming evidence, and then fixing and verifying the solution. ```text @codex-fable5 Debug this failure. Reproduce it first, keep multiple hypotheses, gather disconfirming evidence, then fix and verify. ``` -------------------------------- ### Check FableCodex Source-Heading Coverage Source: https://github.com/baskduf/fablecodex/blob/main/README.md Run this Python script to check the coverage of source headings against Codex-native decisions. Ensure you have a local copy of CLAUDE-FABLE-5.md. ```bash python3 plugins/codex-fable5/skills/codex-fable5/scripts/fable_coverage.py \ --source /path/to/CLAUDE-FABLE-5.md ``` -------------------------------- ### Set Anthropic API Key Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/provider-bridge.md Set the ANTHROPIC_API_KEY environment variable for LiteLLM to authenticate with Anthropic. ```bash export ANTHROPIC_API_KEY="sk-ant-..." ``` -------------------------------- ### Strict Mode Command Source: https://github.com/baskduf/fablecodex/blob/main/README.md Use this command for strict execution, including a goal ledger, review findings, and ensuring tests and findings gate pass before completion. ```text @codex-fable5 Run this strictly. Use a goal ledger, record any review findings, and do not finish until tests and findings gate pass. ``` -------------------------------- ### Final Goal Verification Checkpoint Source: https://github.com/baskduf/fablecodex/blob/main/README.md Completes the final goal, including verification evidence and a command to run tests. This ensures the entire process is verified. ```bash codex-fable5 goals checkpoint \ --id G003 \ --status complete \ --evidence "Implemented quoted CSV parsing and updated tests." \ --verify-cmd "python3 -m unittest discover -s tests -v" \ --verify-evidence "All tests passed." ``` -------------------------------- ### Invoke FableCodex Skill with Lighter Pass Source: https://github.com/baskduf/fablecodex/blob/main/README.md Use the @codex-fable5 skill with a prompt for a quicker review, omitting the goal ledger and focusing on actionable findings. ```text @codex-fable5 Review this quickly. Do not create a goal ledger. Check the key evidence and report only actionable findings. ``` -------------------------------- ### Codex Provider Configuration Source: https://github.com/baskduf/fablecodex/blob/main/plugins/codex-fable5/skills/codex-fable5/references/provider-bridge.md Configure Codex to use a LiteLLM-based provider for Anthropic models. This TOML configuration should be placed in your user-level ~/.codex/config.toml. ```toml model_provider = "litellm-fable5" model = "claude-fable-5" [model_providers.litellm-fable5] name = "LiteLLM Fable 5" base_url = "http://127.0.0.1:4000/v1" env_key = "LITELLM_API_KEY" env_key_instructions = "Set LITELLM_API_KEY to the LiteLLM virtual key or any accepted proxy key." wire_api = "responses" ``` -------------------------------- ### Invoke FableCodex Skill with Detailed Workflow Source: https://github.com/baskduf/fablecodex/blob/main/README.md Use the @codex-fable5 skill with a prompt that specifies a detailed workflow including goal ledgers, findings tracking, and test verification. ```text @codex-fable5 Use this skill to implement the change. Create a goal ledger if the work has multiple steps. Track findings before final completion. Run the project tests before saying it is done. ``` -------------------------------- ### Analysis Only Command Source: https://github.com/baskduf/fablecodex/blob/main/README.md This command instructs FableCodex to analyze code without making any modifications. It provides findings with file and line references. ```text @codex-fable5 Analyze only. Do not edit files. Give findings with file and line references. ``` -------------------------------- ### Resolve a Finding Source: https://github.com/baskduf/fablecodex/blob/main/README.md Resolve a finding after the fix and verification are complete. Include evidence of resolution and verification commands/evidence. ```bash codex-fable5 findings resolve \ --id F001 \ --evidence "Final checkpoints now require verification evidence." \ --verify-cmd "python3 -m unittest discover -s tests -v" \ --verify-evidence "Regression test passed." ``` -------------------------------- ### Compile Python Scripts Source: https://github.com/baskduf/fablecodex/blob/main/CONTRIBUTING.md Compile specified Python scripts to check for syntax errors before submitting a pull request. This helps ensure code integrity. ```bash python -m py_compile \ plugins/codex-fable5/skills/codex-fable5/scripts/codex_goals.py \ plugins/codex-fable5/skills/codex-fable5/scripts/fable_coverage.py \ plugins/codex-fable5/skills/codex-fable5/scripts/make_litellm_config.py \ tests/test_scripts.py ``` === COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.