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.
git clone --depth 1 https://github.com/danielraffel/generous-corp-marketplaceWrote 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/danielraffel/generous-corp-marketplace/config)<a href="https://agentmods.dev/commands/danielraffel/generous-corp-marketplace/config"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/config/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/commands/danielraffel/generous-corp-marketplace/config"><img src="https://agentmods.dev/badge/commands/danielraffel/generous-corp-marketplace/config.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 | $0.00017 | $0.00614 |
| Opus 5 | $0.00009 | $0.00307 |
| Sonnet 5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
config 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You configure and launch /orchestrate:start. You NEVER show a summary table. You NEVER say "copy the command."
Input
Task prompt: $ARGUMENTS
Step 1: Get Prompt
If $ARGUMENTS is empty, ask for a task prompt and wait. Otherwise continue.
Step 2: Preview and Configure
Classify the prompt as Debugging, Feature, Refactor, or Research. Show a one-line type detection and brief team preview.
Then call AskUserQuestion with these 4 questions in a SINGLE call:
Q1 (header: "Mode"):
- "Review & Run (Recommended)" — "See plan summary before executing"
- "Auto-run" — "Execute immediately"
- "Dry-run" — "Output text only for copy/paste"
Q2 (header: "Models"):
- "Smart defaults (Recommended)" — [type-specific: Debug="All Sonnet", Feature/Refactor="Opus lead + Sonnet", Research="Opus Synthesizer + Sonnet"]
- "All Sonnet" — "Cost-efficient"
- "All Opus" — "Maximum capability"
- "All Haiku" — "Fastest, cheapest"
Q3 (header: "Approval"):
- "Auto (Recommended)" — "On for code, off for research"
- "Always on" — "All plans reviewed"
- "Never" — "Skip approval"
Q4 (header: "Go"):
- "Launch (Recommended)" — "Start the orchestration now"
- "Show command" — "Display the command text instead"
- "Cancel" — "Stop without running"
Step 3: Handle Q4 Answer
When you receive all 4 answers, look at Q4:
If Q4 = "Launch": Build args (prompt + non-default flags) and call the Skill tool:
- Auto-run →
--auto-run| Dry-run →--dry-run - All Sonnet →
--models sonnet| All Opus →--models opus| All Haiku →--models haiku - Always approval →
--require-plan-approval true| Never →--require-plan-approval false - Default/Auto/Recommended selections → no flags
Then call: Skill(skill: "orchestrate:start", args: "[prompt] [flags]")
If Q4 = "Show command": Display the /orchestrate:start [prompt] [flags] command as text.
If Q4 = "Cancel": Say "Cancelled." and stop.
IMPORTANT: If Q4 is "Launch", do NOT display a summary table, settings table, or "copy the command" text. Your ONLY action is to call the Skill 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.
- 9d ago First seen · 60 lines · 17 tokens per session scan A 98747838123d
config is a command published in the GitHub repository danielraffel/generous-corp-marketplace (11 stars, last pushed 10d ago), licensed MIT. It adds 17 tokens to every session and 614 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 2026-08-30.
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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.