agentleFS
thebiglaskowskithebiglaskowski/claude-sentient/.claude/commands/CLAUDE.md

claude-sentient / commands

CLAUDE.md2 starsChanged 7 months agoMITView on GitHub

Context for working on /cs-* command files. All commands use YAML frontmatter + XML-structured instructions: Claude Sentient automates documentation based on task context: During /cs-loop INIT, rules are loaded by task keywords. Full mapping: .claude/rules/_index.md Commands can invoke each other via the Skill tool:

The file

We split this CLAUDE.md into the rules it gives an agent

7 rules. About 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All commands use YAML frontmatter + XML-structured instructions:

    line 7
  2. Very specific:

    Create .claude/commands/cs-{name}.md with frontmatter

    line 95
  3. Very specific:

    Use XML tags (<role>, <task>, <steps>, <avoid>, etc.)

    line 96
  4. Very specific:

    Add <avoid> section with command-specific anti-patterns

    line 97
  5. Very specific:

    Update cs-validate.md required commands list

    line 98
  6. Distinctive:

    Update root CLAUDE.md commands table

    line 99
  7. Very specific:

    Update README.md, CHANGELOG.md, install.sh, install.ps1

    line 100

≈ “Common” is an estimate: at least 1 in 5 of the 28,029 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Commands — Claude Sentient

Context for working on /cs-* command files.

Command File Structure

All commands use YAML frontmatter + XML-structured instructions:

---
description: What the command does
argument-hint: <args>
allowed-tools: Tool1, Tool2, ...
---

# /cs-command-name

<role>Expert persona for this command</role>
<task>Clear objective statement</task>
<context>Background info, tables, nested data</context>
<steps>Ordered procedure with <thinking> blocks</steps>
<criteria>Success metrics</criteria>
<output_format>Response structure</output_format>
<constraints>Rules and limitations</constraints>
<avoid>Command-specific DON'Ts</avoid>
<examples>Sample inputs/outputs</examples>

Documentation Policy

Claude Sentient automates documentation based on task context:

Auto-Update Triggers

Change TypeSTATUS.mdCHANGELOG.mdDECISIONS.md
Feature addedAutoConfirmOnly if architectural
Bug fixedAutoConfirm--
RefactoringAuto--If significant
Breaking changeAutoConfirm (required)Required
Config changeAuto----

Automation Levels

LevelWhenExamples
Fully AutoLow risk, high valueRule loading, STATUS.md updates
Auto + ConfirmSignificant changesCHANGELOG entries, version bumps
On RequestUser preferenceFull docs rewrites, ADRs

Rule Auto-Loading

During /cs-loop INIT, rules are loaded by task keywords. Full mapping: .claude/rules/_index.md


Skill Chaining

Commands can invoke each other via the Skill tool:

FromToWhen
/cs-plan/cs-loopAfter plan approval, user chooses to execute
/cs-status/cs-loopWhen pending tasks exist, user chooses to continue
/cs-validate/cs-loopWhen issues found, user chooses to auto-fix
/cs-loop/cs-initWhen no CLAUDE.md detected during INIT
/cs-init/cs-loopAfter creating CLAUDE.md, user chooses to start working
/cs-loop/cs-teamWhen team eligibility detected, user approves team mode
/cs-team/cs-loopWhen team completes, fallback to solo for remaining work
/cs-assess/cs-loopWhen issues found, user chooses to fix them
/cs-review/cs-loopWhen PR changes needed, user chooses to fix
/cs-loop/cs-docsAt COMMIT, when changed files need doc sync check
/cs-docs/cs-loopAfter generating doc, user chooses to implement against spec
/cs-learn—Standalone, appends to learnings.md
/cs-mcp—Standalone, registers/validates MCP servers
/cs-ui/cs-loopWhen UI issues found, user chooses to fix
/cs-deploy—Standalone, read-only deployment readiness check
/cs-sessions/cs-loopWhen user chooses to resume a previous session
/cs-multi—Standalone, configures per-phase model routing
/cs-debug/cs-loopWhen root cause requires implementation changes, user chooses to fix
/cs-log/cs-loopWhen logging gaps/issues found, user chooses to fix
/cs-batch/cs-loopEach worktree agent runs /cs-loop for its work stream
/cs-batch/cs-planWhen argument is a task description, creates plan first
/cs-schedule—Standalone, wraps native /schedule with CS command integration

Adding a New Command

  1. Create .claude/commands/cs-{name}.md with frontmatter
  2. Use XML tags (<role>, <task>, <steps>, <avoid>, etc.)
  3. Add <avoid> section with command-specific anti-patterns
  4. Update cs-validate.md required commands list
  5. Update root CLAUDE.md commands table
  6. Update README.md, CHANGELOG.md, install.sh, install.ps1

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.