Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/gobing-ai/superskill/command-refinegit clone --depth 1 https://github.com/gobing-ai/superskillWhat 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 | $0.00008 | $0.00512 |
| Opus 5 | $0.00004 | $0.00256 |
| Sonnet 5 | $0.00002 | $0.00102 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
command-refine 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 2d ago.
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.
What it actually says
Command Refine
Wraps cc:cc-commands skill.
Run evaluation, apply deterministic structural fixes (missing fields, type coercion, whitespace), then re-evaluate — all in one step. Delegates to cc:cc-commands skill.
When to Use
- Improve command quality after scaffolding
- Fix command issues without running evaluate separately
Arguments
| Argument | Description | Default |
|---|---|---|
<nameOrPath> |
Command name or path to its .md file | (required) |
--auto |
Skip interactive prompts (auto-apply fixes) | false |
--save |
Persist the evaluation to the evaluation store | false |
--dry-run |
Preview classified fixes and projected delta without writing | false |
--target |
Target platform | claude |
Examples
# Refine a command (evaluate + structural fixes + re-evaluate)
/cc:command-refine ./commands/my-command.md
# Auto-refine without prompts
/cc:command-refine ./commands/my-command.md --auto --save
# Preview fixes without writing
/cc:command-refine ./commands/my-command.md --dry-run
Content Fix Types
Beyond deterministic structural fixes, refine applies two named content fix types: description prune (three description rules: front-loaded identity, one trigger per branch, no body restatement) and the pruning pass (no-op hunt — delete don't trim; duplication collapse; sediment removal; disclosure moves). Single copy: cc:cc-skills workflows reference § "Content fix types".
Implementation
Pass $ARGUMENTS to the underlying skill for processing.
Delegates to cc:cc-commands skill:
Skill(skill="cc:cc-commands", args="refine $ARGUMENTS")
Direct CLI execution (all platforms):
superskill command refine $ARGUMENTS
Platform Notes
- Claude Code: Invoke via
Skill()delegation - Other platforms: Run
superskillCLI directly via Bash tool
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.
- 2d ago First seen · 66 lines · 8 tokens per session scan A 69e58354e3ec
command-refine is a command published in the GitHub repository gobing-ai/superskill (5 stars, last pushed 6d ago), licensed Apache-2.0. It adds 8 tokens to every session and 512 once invoked, about $0.0000 per session on Opus 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 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.