Coding standards skill update: symlink as rules

.claude/rules/agents/agent-domain-focus.md

@@ -0,0 +1 @@
+../../../docs/guidance/agent-building-guidelines/agent-domain-focus.md

.claude/rules/agents/agent-external-files.md

@@ -0,0 +1 @@
+../../../docs/guidance/agent-building-guidelines/agent-external-files.md

.claude/rules/agents/agent-model-selection.md

@@ -0,0 +1 @@
+../../../docs/guidance/agent-building-guidelines/agent-model-selection.md

.claude/rules/agents/graceful-degradation.md

@@ -0,0 +1 @@
+../../../docs/guidance/agent-building-guidelines/graceful-degradation.md

.claude/rules/agents/multi-agent-economics.md

@@ -0,0 +1 @@
+../../../docs/guidance/agent-building-guidelines/multi-agent-economics.md

.claude/rules/plugin-entity-taxonomy.md

@@ -0,0 +1 @@
+../../docs/guidance/plugin-entity-taxonomy.md

.claude/rules/skills/allowed-tools-AskUserQuestion.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/allowed-tools-AskUserQuestion.md

.claude/rules/skills/allowed-tools-bash-permissions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/allowed-tools-bash-permissions.md

.claude/rules/skills/context-hygiene.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/context-hygiene.md

.claude/rules/skills/context-injection-commands.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/context-injection-commands.md

.claude/rules/skills/cowork-specific-skill-instructions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/cowork-specific-skill-instructions.md

.claude/rules/skills/documentation-maintenance.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/documentation-maintenance.md

.claude/rules/skills/dynamic-project-discovery.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/dynamic-project-discovery.md

.claude/rules/skills/graceful-degradation.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/graceful-degradation.md

.claude/rules/skills/hardening-fuzzy-vs-deterministic.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/hardening-fuzzy-vs-deterministic.md

.claude/rules/skills/naming-conventions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/naming-conventions.md

.claude/rules/skills/optional-git-repositories.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/optional-git-repositories.md

.claude/rules/skills/progressive-disclosure.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/progressive-disclosure.md

.claude/rules/skills/script-execution-instructions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/script-execution-instructions.md

.claude/rules/skills/security-restrictions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/security-restrictions.md

.claude/rules/skills/skill-composition.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/skill-composition.md

.claude/rules/skills/skill-decomposition.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/skill-decomposition.md

.claude/rules/skills/skill-description-frontmatter.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/skill-description-frontmatter.md

.claude/rules/skills/skill-reference-files.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/skill-reference-files.md

.claude/rules/skills/success-criteria-and-testing.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/success-criteria-and-testing.md

.claude/rules/skills/troubleshooting.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/troubleshooting.md

.claude/rules/skills/use-case-planning.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/use-case-planning.md

.claude/rules/skills/workflow-patterns.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/workflow-patterns.md

.claude/rules/skills/writing-effective-instructions.md

@@ -0,0 +1 @@
+../../../docs/guidance/skill-building-guidance/writing-effective-instructions.md

docs/guidance/agent-building-guidelines/agent-domain-focus.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/agents/**/*.md"
+---
+
 # Domain Focus in Agent Definitions
 
 Agents perform better when they target a narrow domain with precise vocabulary. A focused agent activates deep expertise in the model. A broad generalist activates shallow, averaged knowledge across competing domains.

docs/guidance/agent-building-guidelines/agent-external-files.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/agents/**/*.md"
+---
+
 # External File References in Agent Definitions
 
 Agent definitions are self-contained markdown files. Unlike skills, agents do not support external file references. No `references/` folders, no `scripts/` folders, and no context injection commands. All content must be inlined directly in the agent `.md` file.

docs/guidance/agent-building-guidelines/agent-model-selection.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/agents/**/*.md"
+---
+
 # Choosing the Right Model for Agent Definitions
 
 Agents support a `model` frontmatter field that skills do not. Choosing the right model is about matching capability and speed to the task the agent performs. **Cost is not a factor in model selection for our agents.** Choose based on what the task demands, not price.

docs/guidance/agent-building-guidelines/graceful-degradation.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/agents/**/*.md"
+---
+
 # Graceful Degradation
 
 Agent definitions are self-contained and dispatched by skills. When a skill operates in degraded mode (for example, no git), the agents it dispatches may include steps that depend on git history, branch context, or other tools that may be absent. Without this guidance, agents that fail or produce errors when a tool is missing force the orchestrating skill to add defensive guards around every agent dispatch. An agent that checks tool availability inline and skips gracefully self-adapts to degraded environments.

docs/guidance/agent-building-guidelines/multi-agent-economics.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/agents/**/*.md"
+---
+
 # Multi-Agent Economics
 
 When a skill dispatches agents via the `Agent` tool, each agent adds latency and token cost. This doc provides the decision framework for when adding agents is justified and when it's wasteful.

docs/guidance/skill-building-guidance/allowed-tools-AskUserQuestion.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # `AskUserQuestion` in Skill `allowed-tools`
 
 The `allowed-tools` frontmatter in a SKILL.md file defines which tools are auto-approved without user permission prompts when the skill is active. Due to a bug in Claude Code's permission evaluator, `AskUserQuestion` must not be listed in `allowed-tools` — doing so silently breaks the tool's interactive prompt.

docs/guidance/skill-building-guidance/allowed-tools-bash-permissions.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Bash Permission Patterns in `allowed-tools`
 
 The `allowed-tools` frontmatter in a SKILL.md file declares which Bash commands are auto-approved without user permission prompts. Bash permissions use a glob pattern syntax: `Bash(command prefix *)`. Getting the syntax or granularity wrong causes skills to either stall on permission prompts or silently auto-approve unintended commands.

docs/guidance/skill-building-guidance/context-hygiene.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Context Hygiene
 
 Context hygiene is the discipline of keeping a skill's context footprint minimal, well-positioned, and free of stale or irrelevant tokens. Several other guidance docs contain rules that serve this goal — progressive disclosure, frontmatter conciseness, extracting to references/, position-aware ordering, stale-doc audits. This doc explains the mechanisms behind those rules: why they work and what happens when they're violated. It is based on the [Context Hygiene principle](https://jdforsythe.github.io/10-principles/principles/context-hygiene/), adapted for skill-building concerns.

docs/guidance/skill-building-guidance/context-injection-commands.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Context Injection Commands in Skill Files
 
 Context injection commands use the `` !`command` `` syntax to execute a shell command at skill load time and inject its stdout into the skill as runtime context. The command runs **once when the skill loads**, not during each step. This gives skill steps access to dynamic information about the current environment without hardcoding values.
@@ -217,9 +222,10 @@ Real examples organized by purpose, with source file references:
 
 **File/directory discovery:**
 - `` !`find . -maxdepth 1 -name "CLAUDE.md" -type f` `` — check for file (`code-review`, `coding-standard`, `architectural-decision-record`, `investigate`, `iterative-plan-review`, `project-discovery`, `project-documentation`, `test-planning`)
-- `` !`find . -maxdepth 1 -name "AGENTS.md" -type f` `` — check for file (`project-discovery`)
+- `` !`find . -maxdepth 1 -name "AGENTS.md" -type f` `` — check for file (`coding-standard`, `project-discovery`)
 - `` !`find . -maxdepth 1 -name "README*" -type f` `` — check for file (`project-discovery`)
 - `` !`find . -maxdepth 3 -name "project-discovery.md" -type f` `` — find discovery output (`code-review`, `coding-standard`, `architectural-decision-record`, `investigate`, `iterative-plan-review`, `project-documentation`, `test-planning`)
+- `` !`find . -maxdepth 4 -type d -path "*/.claude/rules/coding-standards"` `` — check for path-scoped rules directory (`coding-standard`)
 
 **Tool availability:**
 - `` !`which gh` `` — check for gh CLI (`update-pr-description`, `gh-pr-review`)

docs/guidance/skill-building-guidance/cowork-specific-skill-instructions.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Claude Cowork — Complete Reference
 
 ## What is Cowork?

docs/guidance/skill-building-guidance/documentation-maintenance.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Documentation Maintenance
 
 A skill that worked last month can silently degrade if its SKILL.md or references describe things that have changed. The model follows stale instructions faithfully — stale documentation is active poison, not passive neglect.

docs/guidance/skill-building-guidance/dynamic-project-discovery.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Dynamic Project Discovery
 
 Skills run in whatever repository the user invokes them from. They must discover the project's structure, branch names, and tool availability dynamically rather than hardcoding assumptions.

docs/guidance/skill-building-guidance/graceful-degradation.md

@@ -1,3 +1,9 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+  - "plugin/skills/**/scripts/**"
+---
+
 # Graceful Degradation
 
 **Differentiation from `dynamic-project-discovery.md`:** That doc covers hard prerequisites — tools or capabilities the skill cannot function without at all; when they're missing, the skill stops with a message to the user. This doc covers *partial context* — situations where the environment is usable but some data (a git history, project config, docs directory) is absent. Graceful degradation means detecting what is available, selecting a named execution mode, and continuing to produce useful output.

docs/guidance/skill-building-guidance/hardening-fuzzy-vs-deterministic.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Hardening: Fuzzy vs. Deterministic Steps
 
 Other guidance docs tell you to extract deterministic operations to scripts ([Progressive Disclosure](./progressive-disclosure.md), [Writing Effective Instructions](./writing-effective-instructions.md)). This doc provides the decision framework for recognizing which steps are candidates and classifying them correctly.

docs/guidance/skill-building-guidance/naming-conventions.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Naming Conventions
 
 Consistent naming across plugins, skills, and directories helps users discover and understand what a skill does from its name alone.

docs/guidance/skill-building-guidance/optional-git-repositories.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Optional Git Repositories
 
 Skills that analyze code should treat git as optional. Hard-requiring git breaks skills in common, legitimate scenarios — and the moments when git is *not* fully set up are often the most valuable times to run an analysis skill.

docs/guidance/skill-building-guidance/progressive-disclosure.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Progressive Disclosure
 
 Skills use a three-level information architecture that balances context availability with token efficiency. Each level loads only when needed, keeping Claude's context window focused on what matters for the current task.

docs/guidance/skill-building-guidance/script-execution-instructions.md

@@ -1,3 +1,9 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+  - "plugin/skills/**/scripts/**"
+---
+
 # Script Execution Instructions in SKILL.md
 
 When a skill needs to run shell scripts during its steps, the SKILL.md body must describe the invocation as numbered prose instructions — not fenced code blocks.

docs/guidance/skill-building-guidance/security-restrictions.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Security Restrictions
 
 Skill frontmatter appears in Claude's system prompt. This privileged position means malicious or malformed frontmatter could inject instructions into the system prompt, bypass skill boundaries, or cause silent failures. These restrictions prevent those risks.

docs/guidance/skill-building-guidance/skill-composition.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Skill Composition
 
 Skills should not call other skills via the Skill tool. Sub-skill calls have

docs/guidance/skill-building-guidance/skill-decomposition.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Skill Decomposition
 
 A skill should do one thing well. When a skill handles too many responsibilities, it becomes fragile, hard to debug, and difficult for the LLM to follow consistently. Split monolithic skills into focused units and extract reusable agent definitions.

docs/guidance/skill-building-guidance/skill-description-frontmatter.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Skill Description Frontmatter
 
 The `description` field in SKILL.md frontmatter is the primary mechanism Claude uses to decide when to invoke a skill. Every installed skill's description is always loaded into Claude's context, where descriptions compete against each other for selection. A thin description means missed triggers — users ask for something the skill handles, but Claude doesn't recognize the match. An overbroad description means false triggers — Claude invokes the wrong skill because descriptions overlap without clear boundaries.

docs/guidance/skill-building-guidance/skill-reference-files.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Skill Reference Files
 
 Skills can include reference documents — templates, checklists, examples, and other supporting content — in a `references/` subdirectory within the skill folder. These files are loaded into the skill's context on demand when a step explicitly references them.

docs/guidance/skill-building-guidance/success-criteria-and-testing.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Success Criteria and Testing
 
 How do you know a skill is working? Without defined success criteria, "it seems fine" becomes the bar — and that bar shifts with each conversation. This guide defines three test types that cover whether a skill triggers correctly, executes its workflow, and actually improves outcomes compared to working without it.

docs/guidance/skill-building-guidance/troubleshooting.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Troubleshooting
 
 This guide covers common problems encountered when building and using skills, organized by symptom. Each section describes the symptom, explains the likely cause, and provides a concrete fix.

docs/guidance/skill-building-guidance/use-case-planning.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Use Case Planning
 
 Before writing a SKILL.md, define 2-3 concrete use cases the skill should handle. Use cases ground the skill in real user workflows rather than abstract capabilities, and they become the test cases you run after building.

docs/guidance/skill-building-guidance/workflow-patterns.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Workflow Patterns
 
 Skills encode workflows — multi-step processes that Claude executes in a specific order with specific tools. This guide documents four structural patterns that appear across well-built skills. Each pattern solves a different workflow shape, and most real skills combine two or more.

docs/guidance/skill-building-guidance/writing-effective-instructions.md

@@ -1,3 +1,8 @@
+---
+paths:
+  - "plugin/skills/**/*.md"
+---
+
 # Writing Effective Instructions
 
 The SKILL.md body — everything below the YAML frontmatter — is where you tell Claude *how* to execute the skill. These instructions load when the skill triggers (Level 2 in the progressive disclosure model) and guide Claude through the workflow step by step.