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/random6913/claude-code-superkit/workflowgit clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkitWrote 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/commands/random6913/claude-code-superkit/workflow)<a href="https://agentmods.dev/commands/random6913/claude-code-superkit/workflow"><img src="https://agentmods.dev/badge/commands/random6913/claude-code-superkit/workflow.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02098 |
| Opus 5 | $0.00012 | $0.01049 |
| Sonnet 5 | $0.00005 | $0.00420 |
| Haiku 4.5 | $0.00002 | $0.00210 |
Grade A, and why
workflow 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Templates
Run one of six opinionated workflow templates. Each template fixes an ordered list of phases and the agents to dispatch, so common task types follow the same proven path every time.
Target
$ARGUMENTS
Hard Rules
- Run only the template named in Target. If Target names none, or the first word matches no template, do not guess — follow Step 3 or Step 4 and stop until the user answers.
- Execute a template's phases in listed order. A phase begins only after the previous phase's done-when condition holds.
- Report status after every phase, and emit the Workflow Report only when every executed phase has a status row.
- On a failed gate or retry, escalate effort to
maxfor the next attempt and state that you are doing so — never silently re-run at the same effort. - spike produces a report only (no code changes); hotfix applies the minimal fix (no refactoring, no improvements).
- When consuming security-scanner output, use its exact enums — Severity CRITICAL/WARNING/SUGGESTION, Confidence HIGH/MEDIUM/LOW.
- For tasks that fit no template, tell the user to use
/devinstead of forcing a template.
Steps
- Read the template name from the first word of Target. Done when: the name equals one of the six templates below, or you route to Step 3/4.
- Read the task description from the rest of Target. Done when: the task text is captured (empty is allowed — spike and security-audit can run without a description).
- If Target names no template — list the six templates with their one-line summaries and ask the user to choose. Done when: the user names a template; do not proceed before then.
- If the first word matches no template — name the single closest template and ask the user to confirm before running it. Done when: the user confirms or picks another; do not proceed before then.
- Run the matched template's phases (see Templates) in order. At each dispatch point, dispatch the named agent; if that agent is absent from
.claude/agents/, perform the phase inline and write "agent unavailable — ran inline" in that phase's Notes. Done when: every phase's done-when condition is met. - After each phase, record its status row for the Workflow Report (see Output). Done when: Step 5's final phase done-when holds and every executed phase has a row — only then emit the report.
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 · 151 lines · 24 tokens per session scan A 3bad92dee1d4
workflow is a command published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 2,098 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
triage-issue
Apply labels + milestone + priority to a new issue using the llmwiki triage rules.
team
Build a team of Conductor workspaces (with roles) and dispatch tasks to it.
init
Initialize dev-flow project — scan current state, create/align .dev-doc, update agent instruction file.
issue-implement
Implement a specific stage of an issue's implementation plan using feature-dev.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.