Borrowing it
Nothing to install: this file belongs to javimosch/supercli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/javimosch/supercli/master/.agents/skills/supercli-mastery/SKILL.mdgit clone --depth 1 https://github.com/javimosch/supercliWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/javimosch/supercli/supercli-mastery)<a href="https://agentmods.dev/skills/javimosch/supercli/supercli-mastery"><img src="https://agentmods.dev/badge/skills/javimosch/supercli/supercli-mastery/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/javimosch/supercli/supercli-mastery"><img src="https://agentmods.dev/badge/skills/javimosch/supercli/supercli-mastery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01619 |
| Opus 5.5 | $0.00016 | $0.00648 |
| Sonnet 5.5 | $0.00008 | $0.00324 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
supercli-mastery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
supercli-mastery — Agent's Guide to SuperCLI
What SuperCLI Is
SuperCLI is a capability router. It wraps external CLIs (plugins) behind a uniform namespace.resource.action command model. Every command follows the same pattern:
sc <namespace> <resource> <action> --<arg> <value> --json
The workflow is: discover → learn → inspect → plan → execute
Core Capabilities
| Capability | Description |
|---|---|
commands |
Query available commands |
plugins |
Plugin management and discovery |
skills |
Agent-facing skill documents |
inspect |
View command schema |
plan |
Preview execution steps before running |
ask |
LLM suggests which commands to run (no execution) |
mcp |
Model Context Protocol adapter |
Output Conventions
All commands return JSON when --json is used (or by default in non-TTY):
sc <ns> <res> <act> --json
→ { "version": "1.0", "command": "ns.res.act", "data": {...} }
- stdout: Primary data (JSON envelope)
- stderr: Progress events, warnings, structured errors
- Exit code 0: Success
Semantic Exit Codes
| Code | Meaning | Agent action |
|---|---|---|
| 0 | Success | Proceed |
| 82 | Validation error | Fix input arguments |
| 85 | Invalid argument | Fix the args, don't retry |
| 91 | Safety violation | Non-TTY interactive command blocked |
| 92 | Resource not found | Use different ID/name |
| 105 | Integration / API error | Retry with backoff (transient) |
| 110 | Internal error | Report bug, don't retry |
Range convention (Square-style): 80-89 input errors, 90-99 resource errors, 100-109 integration errors, 110-119 internal errors. Currently implemented codes listed above; unused slots reserved for future granularity.
Agent Workflow
1. Discover — Find what's available
sc --json
# → lists first_steps with {command, purpose} pairs
sc commands --query backup --limit 50 --json
# → { commands: [{ namespace, resource, action, description }] }
sc plugins explore --name <tool> --json
# → { plugins: [{ name, description, tags, installed }] }
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 207 lines · 40 tokens per session scan A 23b089a1e087
supercli-mastery is a skill published in the GitHub repository javimosch/supercli (56 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,619 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-29.
Other skills, from other repositories
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
topos
Manage the shared team skills and MCP servers topos delivers to this machine — see what is managed, update it, add more, and share local improvements back. Use when editing anything in a skills directory, when the user asks about team skills, skill updates, or sharing a skill, when setting up topos for a team or a…
update-harness
Update an existing Claude Code harness — check for outdated components, duplication with official features, missing patterns, and improvement opportunities, then apply approved changes. Use whenever: 'update harness', 'update my harness', 'is my harness up to date', 'harness outdated', 'optimize harness', 'check my…
create-harness
Generate a complete, project-specific Claude Code harness — agents, skills, hooks, CLAUDE.md rules — tailored to any codebase. Use whenever someone says 'create a harness', 'set up agents for this project', 'configure Claude Code', 'build an agent team', 'make this project AI-ready', 'harness this project', or any…
github-copilot-cli-expert
Expert knowledge of GitHub Copilot CLI - installation, configuration, usage, custom agents, MCP servers, and version management. Use when asking about copilot cli, copilot commands, installing copilot, updating copilot, copilot features.
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…