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 skills add LandonSchropp/agent-toolkit --skill parallelizegit clone --depth 1 https://github.com/LandonSchropp/agent-toolkitWrote 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/skills/landonschropp/agent-toolkit/parallelize)<a href="https://agentmods.dev/skills/landonschropp/agent-toolkit/parallelize"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/parallelize/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/skills/landonschropp/agent-toolkit/parallelize"><img src="https://agentmods.dev/badge/skills/landonschropp/agent-toolkit/parallelize.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 | $0.00039 | $0.00470 |
| Opus 5.5 | $0.00016 | $0.00188 |
| Sonnet 5.5 | $0.00008 | $0.00094 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
parallelize 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallelize
Turn a set of tasks into an ordered set of stages: what can run at the same time, and what has to wait for something else to land first. The goal is the most parallelism the dependencies allow, with no two agents doing overlapping work.
Workflow
- Gather the tasks. Where they are Linear issues, fetch them with the Linear MCP server so each one carries its own description rather than a title.
- Copy
assets/parallelization.mdto/tmp/[title].md, slugifying the title. - Fill in the tasks, then sort them into stages. A task belongs in the earliest stage whose predecessors have all finished.
- Look for overlaps: two tasks that would edit the same files, or that both have to add the same thing before they can start. Split, merge, or sequence them so no two agents in the same stage collide.
- Present the stages to the user as a table (columns: Stage, Tasks, Waiting On).
- Invoke the
ls-interactivity:interactive-editskill with the file so the user can adjust it, then read their changes back. Where that skill isn't available, post the file's contents in the conversation instead, wait for the user's reply, and update the file with their changes.
Rationalizations
| Thought | Reality |
|---|---|
| "I'll start the first stage while we talk" | This skill only plans. Executing the stages is a separate step. |
| "Everything looks independent, one stage" | Check what they edit. Shared files are a dependency you missed. |
| "I'll assign branches while I'm in here" | Not this skill's call. The agent executing a task decides where work lands. |
| "Two tasks overlap, I'll let them race" | Two agents editing one file is a conflict you chose. Sequence them. |
| "The table is approved, the file can differ" | The file is what gets executed. Fix it, not just the table. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed 055f35bbd455
- 1mo ago Changed · +1 lines · +3 tokens per session e3c76c081632
- 1mo ago First seen · 27 lines · 36 tokens per session scan A afbd6e376320
parallelize is a skill published in the GitHub repository LandonSchropp/agent-toolkit (3 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 470 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
cf-cli
Cloudflare's official cf CLI (beta) for the public Cloudflare API and Workers projects. Use for finding and running Cloudflare commands from the terminal — sign-in and profiles, cf cli search, cf schema, cf deploy/dev/build, resource commands for DNS, zones, D1, KV, and R2 — and for choosing between cf and Wrangler in…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list without guessed contacts.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.
ai-visibility-writing
Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite its useful information. Use when someone asks for AI visibility, AI search, answer-engine, AEO, GEO, AI Overview, or…