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/Marcel-Bich/marcel-bich-claude-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/marcel-bich/marcel-bich-claude-marketplace/parallel)<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/parallel"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/parallel/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/marcel-bich/marcel-bich-claude-marketplace/parallel"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/parallel.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 | $0.00011 | $0.00795 |
| Opus 5 | $0.00005 | $0.00398 |
| Sonnet 5 | $0.00002 | $0.00159 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
parallel 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 6d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Worktree Parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.
Arguments
$ARGUMENTS is parsed as a pipe-separated list of tasks:
worktree1:prompt1 | worktree2:prompt2 | worktree3:prompt3
Example:
/hydra:parallel feature-a:Implement login | feature-b:Implement logout | feature-c:Write tests
Process
1. Parse Tasks
Split $ARGUMENTS at | and parse each part:
# Example parsing
echo "$ARGUMENTS" | tr '|' '\n' | while read task; do
WORKTREE=$(echo "$task" | cut -d':' -f1 | xargs)
PROMPT=$(echo "$task" | cut -d':' -f2- | xargs)
echo "Worktree: $WORKTREE, Prompt: $PROMPT"
done
2. Validate All Worktrees
For each task:
git worktree list | grep -qE "$WORKTREE|hydra/$WORKTREE"
If a worktree is missing, offer to create it:
The following worktrees do not exist:
- feature-x
- feature-y
Should I create them? (Branches will be forked from main)
If yes, create missing worktrees:
# Determine paths (always relative to repo root, not CWD)
REPO_ROOT=$(git rev-parse --show-toplevel)
REPO_NAME=$(basename "$REPO_ROOT")
WORKTREES_DIR="$(dirname "$REPO_ROOT")/${REPO_NAME}-worktrees"
for WT in feature-x feature-y; do
git worktree add -b "hydra/$WT" "$WORKTREES_DIR/$WT"
done
3. Start All Agents in Parallel
IMPORTANT: Use a single response with multiple Task tool calls!
For each task, call Task tool with:
subagent_type: general-purpose
run_in_background: true
prompt: [like in /hydra:spawn]
All Task calls must be in ONE response for true parallelism.
4. Collect Results
After starting all agents:
Parallel agents started:
Worktree | Agent ID | Task
--------------|-----------------|---------------------------
feature-a | agent-abc123 | Implement login
feature-b | agent-def456 | Implement logout
feature-c | agent-ghi789 | Write tests
All agents running in background.
Next steps:
- /hydra:status # Progress of all worktrees
- TaskOutput agent-abc123 # Result of one agent
- /hydra:merge feature-a # When done: merge individually
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.
- 6d ago First seen · 138 lines · 11 tokens per session scan A 47e4a55f15e0
parallel is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 795 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
init-project
Initialize project with CLAUDE.md template - adaptive detection for new or existing projects.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
changelog
Generate a changelog entry from git commits since the last tag using conventional commit format.
deploy
Deploy application with pre/post-deploy checks.
auto-claude
Invoke Auto-Claude autonomous coding framework for complex feature implementation.
update-counts
Update all hardcoded counts (skills, agents, marketplace repos/skills) across documentation from filesystem.