slash-commander
Skill1 starsChanged 10 days agoMITView on GitHub
Bridges .agents workflows to real Claude Code slash commands and audits that the link between commands/*.md and workflows/*.md never drifts.
- Deletes or force-pushes
In this repository37 other files it gives its agents.
- agents.mdAGENTS.md
- skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibilitySkill
- autoskillsSkill
- compliance-checkerSkill
- contract-writerSkill
- django-expertSkill
- django-patternsSkill
- django-securitySkill
- django-tddSkill
- django-verificationSkill
- env-shielding-auditorSkill
- frontend-designSkill
- graphifySkill
- js-standardizerSkill
- mass-standardizerSkill
- mcp-registrySkill
- nodejs-backend-patternsSkill
- nodejs-best-practicesSkill
- omni-context-minimizerSkill
- python-quality-auditorSkill
- readme-standardizerSkill
- seoSkill
- skill-creatorSkill
- skilloptSkill
- skills-samplesSkill
- sprint-architectSkill
- tailwind-css-patternsSkill
- token-saver-auditorSkill
- topology-monitorSkill
- topology-scaffolderSkill
- typescript-advanced-typesSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- viteSkill
The file
Files
☄️ Skill: Slash Commander
1. How the bridge actually works
Real Claude Code discovers slash commands by scanning .claude/commands/**/*.md in the host project root — there is no runtime generation step. The bridge is:
- Source of truth: each
workflows/<name>_workflow.mdhas a matching, hand-authoredcommands/<name>.mdin this submodule (frontmatterdescription+ a body that@-references the workflow file). - Installation:
python3 .agents/scripts/install.pysymlinkscommands/<name>.mdinto the host's.claude/commands/agents/<name>.md, which Claude Code then exposes as/agents:<name>. - Drift check:
scripts/verify_commands.py(this skill) scanscommands/*.mdfor@.agents/workflows/...references and fails if any points at a workflow file that doesn't exist. Run it after adding/renaming a workflow, or as part ofaudit_workflow.md'slink_auditstep.
2. Command Mapping
| Workflow | Command | Slash invocation |
start_workflow.md | commands/start.md | /agents:start |
close_workflow.md | commands/close.md | /agents:close |
pipeline_workflow.md | commands/pipeline.md | /agents:pipeline |
extract_workflow.md | commands/extract.md | /agents:extract |
| (new workflow) | new commands/<name>.md | /agents:<name> |
3. Governance Constraints
- Isolation: The installer MUST NOT overwrite anything under host
.claude/that isn't already a symlink back into.agents/— it skips and warns on collisions instead. - Mirroring: A change to a workflow file's
descriptionfrontmatter should be reflected by hand in its pairedcommands/<name>.md(no auto-sync exists;verify_commands.pyonly checks the reference resolves, not that the description text matches).
4. Error Handling
- Broken reference:
verify_commands.pyexits non-zero and lists every command pointing at a missing workflow. - Bridge not installed / desynced:
hooks/on_init.pyrunsscripts/install.pyautomatically at session start whenever.agents/.bridge_claude.lockis missing, its recorded commit is stale, or the linked.claude/artifacts are missing despite a matching lock (bridge_intactsentinel check — catches agit clean -fd/manual deletion of the host's untracked bridge, which the lock alone can't detect).
Optimized for the Token-Optimized Agent Pipeline, Rule 113.
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
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.

