Nanoclaw Repl
This is ECC's session-aware REPL wrapper around claude -p that stores everything in markdown files. You get persistent conversation history, model switching, dynamic skill loading, and session branching without pulling in any npm dependencies. The markdown-as-database approach is clever: your session state lives in plain text files you can grep, diff, and version control. If you're already using claude -p for scripting and want conversation memory plus the ability to fork your context before trying something risky, this gives you that. The zero-dependency constraint means it stays portable and auditable, though you're trading ecosystem conveniences for simplicity.
- skills.sh installs
- 5.4K
- GitHub stars
- 300.3K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add affaan-m/ecc --skill nanoclaw-repl --agent claude-codeInstalls into .claude/skills of the current project.
Files
NanoClaw REPL
Use this skill when running or extending scripts/claw.js.
Capabilities
- persistent markdown-backed sessions
- model switching with
/model - dynamic skill loading with
/load - session branching with
/branch - cross-session search with
/search - history compaction with
/compact - export to md/json/txt with
/export - session metrics with
/metrics
Operating Guidance
- Keep sessions task-focused.
- Branch before high-risk changes.
- Compact after major milestones.
- Export before sharing or archival.
Extension Rules
- keep zero external runtime dependencies
- preserve markdown-as-database compatibility
- keep command handlers deterministic and local
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/affaan-m/ecc
- First seen
- Jul 14, 2026
More from affaan-m/ecc
All 263- Messages Ops5.4K
- Recsys Pipeline Architect5.4K
- Latency Critical Systems5.3K
- Fsharp Testing5.3K
- Tinystruct Patterns5.3K
- Uncloud5.3K
- Parallel Execution Optimizer5.3K
- Prediction Market Oracle Research5.3K
- Prediction Market Risk Review5.3K
- Data Throughput Accelerator5.3K
- Recursive Decision Ledger5.3K
- Team Agent Orchestration5.1K
- Dynamic Workflow Mode5K
- Kubernetes Patterns4.9K
- Intent Driven Development4.8K
- Inherit Legacy Style4.8K
- Orch Build Mvp4.8K
- Codehealth Mcp4.8K
- Orch Pipeline4.8K
- Orch Add Feature4.8K
- Orch Refine Code4.8K
- Orch Fix Defect4.8K
- Orch Change Feature4.8K
- Literature Review3.9K
Recommended
cavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
improveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
karpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs