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/thrashr888/agentkernel/parallelgit clone --depth 1 https://github.com/thrashr888/agentkernelWhat 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 | $0.00000 | $0.00618 |
| Opus 5 | $0.00000 | $0.00309 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentkernel parallel
Run multiple jobs concurrently. Each job runs in its own sandbox. Results are collected and reported when all jobs finish.
Usage
agentkernel parallel --job <JOB> [--job <JOB>...] [-B <BACKEND>]
Options
| Option | Description |
|---|---|
-j, --job <JOB> |
Job spec (repeatable). Format: name:image:command or name:image:tag:command |
-B, --backend <BACKEND> |
Backend to use |
Job Format
Jobs are specified as colon-separated strings:
name:image:command # Image without tag (uses :latest)
name:image:tag:command # Image with explicit tag
Examples:
lint:node:npx eslint .— usesnode:latesttest:node:22-alpine:npm test— usesnode:22-alpinebuild:rust:1.85-alpine:cargo build— usesrust:1.85-alpine
Examples
Run lint and test in parallel
$ agentkernel parallel \
--job "lint:node:22-alpine:npx eslint ." \
--job "test:node:22-alpine:npm test" \
-B docker
Running 2 jobs in parallel...
lint done (1.2s)
test done (3.4s)
All jobs passed (3.4s wall time)
Fan-out across languages
agentkernel parallel \
--job "python:python:3.12-alpine:python3 -c 'print(1+1)'" \
--job "node:node:22-alpine:node -e 'console.log(1+1)'" \
--job "ruby:ruby:3.3-alpine:ruby -e 'puts 1+1'" \
-B docker
Handle failures
$ agentkernel parallel \
--job "pass:alpine:3.24:echo ok" \
--job "fail:alpine:3.24:false" \
-B docker
Running 2 jobs in parallel...
pass done (0.2s)
fail FAILED (0.2s)
Error: Some jobs failed (0.2s wall time)
The exit code is non-zero if any job fails.
How It Works
- All jobs are spawned concurrently using
tokio::spawn - Each job tries ephemeral execution first, then falls back to full sandbox lifecycle
- Results are collected and displayed as jobs complete
- Wall time reflects the slowest job (parallel execution)
See Also
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 · 88 lines · 0 tokens per session scan A d5802449221f
parallel is a command published in the GitHub repository thrashr888/agentkernel (58 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 618 tokens. 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
diagnose
Run sivtr doctor to check the environment, then investigate any failing checks.
test-changed
Run the full quality gate on only the files changed since branching from main.
test_mcp
Test all rust-docs-testing tools found in @rust-docs-mcp/src/service.rs.
update_mcp_tools_list
Read the rust-docs-mcp/src/service.rs module and ensure that the README.md and the rust-docs-mcp/install.sh files have up to date lists of the tools available in the MCP.
review
You are an expert code reviewer. Your job is to review code changes and provide actionable feedback.
speckit.git.feature
Create a feature branch with sequential or timestamp numbering.