batch-pipeline

batch-pipeline is a skill for Claude Code from AratKruglik/claude-sdlc. It costs 164 tokens per session (3,685 once invoked), scanned A, original, MIT.

A runner for processing several independent software tasks in parallel. It gives each task an isolated Git worktree, a separate working copy of the repository, and runs the full delivery pipeline for each one.

In plain words
What is it for?
Use it to batch feature requests, group likely-conflicting work, dispatch isolated pipeline runs, and combine their results into one summary.
Why use it?
It reduces waiting when tasks do not depend on one another while limiting accidental file changes between tasks. Its file-conflict grouping is only a prediction based on task descriptions.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc plugin — 3 skills, 5 commands, 5 agents shipped together

Good fit Use it to batch feature requests, group likely-conflicting work, dispatch isolated pipeline runs, and combine their results into one summary.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add AratKruglik/claude-sdlc
Claude Code
/plugin install sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 3 skills, 5 commands, 5 agents.

Wrote 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.

agentmods badge for batch-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/skills/aratkruglik/claude-sdlc/batch-pipeline/github.svg)](https://agentmods.dev/skills/aratkruglik/claude-sdlc/batch-pipeline)
Your own site
<a href="https://agentmods.dev/skills/aratkruglik/claude-sdlc/batch-pipeline"><img src="https://agentmods.dev/badge/skills/aratkruglik/claude-sdlc/batch-pipeline/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.

agentmods 80×15 button for batch-pipeline

Your own site · 80×15
<a href="https://agentmods.dev/skills/aratkruglik/claude-sdlc/batch-pipeline"><img src="https://agentmods.dev/badge/skills/aratkruglik/claude-sdlc/batch-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,685 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 180
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.03685
Opus 5.5 $0.00066 $0.01474
Sonnet 5.5 $0.00033 $0.00737
Haiku 4.5 $0.00016 $0.00368

Measured 2d ago against content hash 1a0773960b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

batch-pipeline 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.

plugins/sdlc/skills/batch-pipeline/SKILL.md · 333 lines

How it starts

The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch Pipeline

You are the SDLC Batch Runner. You take multiple independent task descriptions, isolate each one in its own git worktree, and dispatch one background agent per task that runs the full pipeline-orchestrator skill end-to-end (BA → Dev → QA → Security → Docs) for that single task. You never write or edit project code directly — that happens inside each task's worktree, by the dispatched agent.


Inputs (from commands/batch.md Step 2)

  • tasks[] — parsed task descriptions (each may carry a [simple] / [complex] complexity hint inline; strip it into CONTEXT.tasks[i].complexity_hint if present).
  • forced_stack — --stack=NAME override, or "auto-detect".
  • dry_run — boolean.

Conflict detection is heuristic — say so

This skill predicts file overlap from task description text only (keyword → likely-path heuristics below). It does not read a real diff — there is no diff yet, since no worktree has touched any files at the point grouping happens. Treat grouping as a conservative scheduling aid, not a guarantee of conflict-free execution. Post-hoc conflicts (if any) surface as a normal PR merge conflict on the target branch, which is outside this skill's scope.


Known limitation: batch branches ignore the learned naming convention

pipeline-orchestrator Step 0b-git detects the project's branch-naming convention and proposes a branch per task (see references/GIT-FLOW.md). Batch runs do not get that branch: isolation comes from the Agent tool's isolation: "worktree" parameter, and the tool names the worktree's branch itself. The orchestrator inside each dispatched agent therefore starts on a branch it did not choose, sees a non-base branch, and continues on it rather than creating a second one.

Consequences to disclose when they matter:

  • Batch branch names do not follow the project's feature/-style convention.
  • The PR base branch is still correct — pr_base_branch is derived from the task type and the detected model, not from the branch name, so a git-flow project's batch PRs still target develop (or main for a hotfix).
  • Each worktree branches from the current base at dispatch time, as already described in Step 2's chaining caveat.

Read the full file on GitHub · 333 lines

Changes

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.

  1. 2d ago Changed · +1 lines 1a0773960b29
  2. 11d ago Changed · +10 lines f6f704a37ff5
  3. 1mo ago First seen · 322 lines · 164 tokens per session scan A bc834aae26a6

Subscribe to this mod's changes

batch-pipeline is a skill published in the GitHub repository AratKruglik/claude-sdlc (53 stars, last pushed 2d ago), licensed MIT. It adds 164 tokens to every session and 3,685 once invoked, about $0.0007 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 2026-09-03.