closedloop-env
$
npx mdskill add closedloop-ai/claude-plugins/closedloop-envAccess ClosedLoop paths and apply organizational learnings.
- Enables file operations on run directories and plugin schemas.
- Depends on .closedloop-ai/env and agent-specific learnings files.
- Selects patterns from previous runs to improve current performance.
- Acknowledges applied patterns to document decision-making.
SKILL.md
.github/skills/closedloop-envView on GitHub ↗
---
name: closedloop-env
description: Provides ClosedLoop environment paths (CLOSEDLOOP_WORKDIR, CLAUDE_PLUGIN_ROOT) to agents. This skill should be used by any agent that needs to access ClosedLoop run directories, plugin schemas, or other path-dependent resources.
---
# ClosedLoop Environment
This skill provides access to ClosedLoop environment variables needed for file operations.
## Get Environment Paths
Read the base environment file:
.closedloop-ai/env
The file contains KEY=VALUE pairs:
- `CLOSEDLOOP_WORKDIR` - The run directory for this session
- `CLAUDE_PLUGIN_ROOT` - The plugin installation directory
- `CLOSEDLOOP_PRD_FILE` - Path to the PRD file
- `CLOSEDLOOP_MAX_ITERATIONS` - Maximum loop iterations
## Common Paths
After reading the env file, construct paths like:
- Schema file: `{CLAUDE_PLUGIN_ROOT}/schemas/plan-schema.json`
- Plan file: `{CLOSEDLOOP_WORKDIR}/plan.json`
## Organization Learnings
Also read your agent-specific learnings file if it exists:
.closedloop-ai/learnings-{your-agent-name}
Where `{your-agent-name}` is your `name:` from your frontmatter in lowercase (e.g., `plan-validator`).
The learnings file contains an `<organization-learnings>` block with patterns from previous runs. These learnings capture what worked well and should be applied to improve your performance.
When learnings are present:
1. Review the patterns before starting your task
2. Apply relevant patterns to your work
3. Acknowledge which patterns you applied in your response using the format specified in the learnings block
More from closedloop-ai/claude-plugins
- artifact-type-tailored-contextCompresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent context
- build-status-cache|
- critic-cache|
- cross-repo-cache|
- decision-tableUse when the user wants a code-grounded decision table for current behavior, wants to compare current behavior against a plan or work item, or needs a control-flow artifact for recovery, retry, finalization, validation, state-machine, or review-heavy edge cases.
- eval-cache|
- extract-plan-md|
- find-plugin-fileThis skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to dynamically resolve plugin file paths.
- learning-qualityStructured format for capturing high-quality learnings during ClosedLoop runs
- mermaid-visualizerThis skill should be used when a user asks to explain a complex idea, concept, or system architecture, or when a diagram would be helpful to visualize control flows, system architectures, data flows, state machines, sequence diagrams, or entity relationships.