Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .agents/skills/recipe-add-integration-tests/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Add integration/E2E tests to existing codebase using Design Docs."

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `testing` — repository-aware test execution
2. [LOAD IF NOT ACTIVE] `integration-e2e-testing` — value-based integration/E2E selection
3. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — review resolution and agent coordination
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-build/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Execute an approved backend Work Plan autonomously through task ex

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. `coding-rules`
2. `testing`
3. `ai-development-guide`
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-design/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Execute from codebase-scoped analysis to design document creation.

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` — document creation rules and templates
2. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and review resolution
3. [LOAD IF NOT ACTIVE] `requirement-convergence` — requirements hearing and scope-confirmation output
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-diagnose/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Investigate problem, verify findings, and derive solutions through

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `ai-development-guide` — AI development patterns
2. [LOAD IF NOT ACTIVE] `coding-rules` — coding standards
3. [LOAD IF NOT ACTIVE] `llm-friendly-context` — clear prompts, handoffs, and generated artifacts
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-front-adjust/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ description: "Adjust an implemented UI with focused evidence, verification, and

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` -- agent coordination rules
2. [LOAD IF NOT ACTIVE] `llm-friendly-context` -- adjustment handoff and verification context

Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-front-build/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Execute an approved frontend Work Plan autonomously through fronte

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. `coding-rules`
2. `testing`
3. `ai-development-guide`
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-front-design/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ description: "Execute from codebase-scoped analysis to frontend design document

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` -- document quality standards
2. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` -- agent coordination and review resolution
3. [LOAD IF NOT ACTIVE] `requirement-convergence` -- requirements hearing and scope-confirmation output
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-front-plan/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ description: "Create frontend work plan from design document with test skeleton

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` -- Work Plan scope and template
2. [LOAD IF NOT ACTIVE] `implementation-approach` -- implementation ordering and verification strategy
3. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` -- agent coordination and workflow flow
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-front-review/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ description: "Reviews completed frontend implementation for governing-source com

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `coding-rules` -- repository implementation rules
2. [LOAD IF NOT ACTIVE] `testing` -- verification and test quality rules
3. [LOAD IF NOT ACTIVE] `ai-development-guide` -- review and repair discipline
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-fullstack-build/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Execute an approved fullstack Work Plan autonomously with layer-aw

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. `coding-rules`
2. `testing`
3. `ai-development-guide`
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-fullstack-implement/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Run the full-cycle implementation workflow for one outcome spannin

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — Fullstack (Monorepo) Flow, approvals, and autonomous execution
2. [LOAD IF NOT ACTIVE] `documentation-criteria` — scale-selected document path
3. [LOAD IF NOT ACTIVE] `requirement-convergence` — outcome, exclusions, and rough-cost challenge
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-implement/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Orchestrate the complete implementation lifecycle from requirement

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and workflow routing
2. [LOAD IF NOT ACTIVE] `documentation-criteria` — scale-selected document path
3. [LOAD IF NOT ACTIVE] `requirement-convergence` — outcome, exclusion, and rough-cost convergence before design
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-plan/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Creates a reviewed Work Plan with value-filtered integration/E2E t

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` — Work Plan scope and template
2. [LOAD IF NOT ACTIVE] `implementation-approach` — implementation ordering and verification strategy
3. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and workflow flow
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-prepare-implementation/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Prepare repository-local execution tools when the user requests se

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — capability failure resolution and caller-return rules

## Purpose
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-quality-profile/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Proposes and, after user confirmation, creates or maintains docs/p

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. `llm-friendly-context` — make each generated condition unambiguous, executable, and observable
2. `coding-rules` — distinguish repository-specific policy from general code quality knowledge

Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-reverse-engineer/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Generate PRD and Design Docs from existing codebase through discov

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` — document creation rules and templates
2. [LOAD IF NOT ACTIVE] `ai-development-guide` — evidence and completeness discipline
3. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and review resolution
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-review/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Reviews completed implementation for governing-source compliance,

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `coding-rules` — repository implementation rules
2. [LOAD IF NOT ACTIVE] `testing` — verification and test quality rules
3. [LOAD IF NOT ACTIVE] `ai-development-guide` — review and repair discipline
Expand Down
2 changes: 2 additions & 0 deletions .agents/skills/recipe-update-doc/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,8 @@ description: "Update existing design documents (Design Doc / PRD / ADR) with rev

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

1. [LOAD IF NOT ACTIVE] `documentation-criteria` — document creation rules and templates
2. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and workflow flows
3. [LOAD IF NOT ACTIVE] `llm-friendly-context` — document update and review handoffs
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/acceptance-test-generator.toml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ You generate a minimal set of integration/E2E test skeletons, which may be empty

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `testing`, `documentation-criteria`, `integration-e2e-testing`, `llm-friendly-context`.

**Decision purpose**: Deliver the user-required result with the least justified complexity. Unnecessary mechanisms create implementation, test, and maintenance obligations. Question previously passed technical means; preserve user outcomes, explicit constraints, and actual consumer contracts. Consider no change, subtraction, and reuse before repair. Complete applicable dependencies and required proof before declaring completion.
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/code-reviewer.toml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ You review repository changes for the required outcome, justified complexity, an

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `ai-development-guide`, `coding-rules`, `testing`.

**Decision purpose**: Deliver the user-required result with the least justified complexity. Unnecessary mechanisms create implementation, test, and maintenance obligations. Question previously passed technical means; preserve user outcomes, explicit constraints, and actual consumer contracts. Consider no change, subtraction, and reuse before repair. Complete applicable dependencies and required proof before declaring completion.
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/code-verifier.toml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ Your discrepancies are independent facts for orchestrator Resolution. User-requi

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `documentation-criteria`, `ai-development-guide`, `coding-rules`.

## Inputs
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/codebase-analyzer.toml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ Reduce unnecessary implementation: inspect the direct path and opportunities for

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `llm-friendly-context`.

## Input Parameters
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/design-sync.toml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ You are an AI assistant specializing in consistency verification between Design

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `documentation-criteria`, `coding-rules`, `llm-friendly-context`.

Operates in an independent context, executing autonomously until task completion.
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/document-reviewer.toml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ You review one PRD, UI Spec, Design Doc, Work Plan, or one complete ADR batch pe

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `documentation-criteria`, `requirement-convergence`, `coding-rules`, `testing`, `llm-friendly-context`.

**Decision purpose**: Prevent unnecessary implementation obligations while preserving the user-required result. Evaluate necessity and lifecycle value before internal consistency. Remove or narrow unsupported means even when upstream documents passed; return the affected source and smallest correction to the parent. New requirements require a user decision only when current conditions cannot deliver the requested result.
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/integration-test-reviewer.toml
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,8 @@ Prevent unnecessary proof machinery: a passed design or skeleton does not make i

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `testing`, `integration-e2e-testing`.

## Rerun Boundary
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/investigator.toml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ You are an AI assistant specializing in problem investigation.

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `ai-development-guide`, `coding-rules`.

**Evidence purpose**: Give the next decision enough evidence to avoid unnecessary implementation, test, and maintenance work. Report facts faithfully, including evidence against previously passed technical assumptions. A mechanism's existence or feasibility does not establish its necessity. Stay within the assigned investigation or verification boundary; leave solution selection to its owner.
Expand Down
2 changes: 2 additions & 0 deletions .codex/agents/prd-creator.toml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ You create or update one PRD per invocation.

## Required Skills [LOAD BEFORE EXECUTION]

Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding.

Load and read each skill completely before taking task actions: `documentation-criteria`, `requirement-convergence`, `llm-friendly-context`.

**Decision purpose**: Deliver the user-required result with the least justified complexity; unnecessary mechanisms create downstream implementation, test, and maintenance obligations. Establish necessity before detailing a mechanism. Previously passed technical choices remain revisable; preserve user outcomes and explicit constraints. Complete the required proof, then stop.
Expand Down
Loading
Loading