spec-splitter

spec-splitter is a command for Claude Code from MarioEpkOne/PipelineIQ. It costs 0 tokens per session (3,959 once invoked), scanned A, original, MIT.

A command that breaks a large software specification into smaller, self-contained specifications. The smaller documents are intended for separate implementation work that can run in parallel.

In plain words
What is it for?
Use it on a specification file before running parallel implementation work, especially when the original specification is too large.
Why use it?
It reduces the amount of context each implementation task must handle and makes large projects easier to divide safely.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the pipelineiq plugin — 10 commands, 6 agents shipped together

Good fit Use it on a specification file before running parallel implementation work, especially when the original specification is too large.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/marioepkone/pipelineiq/spec-splitter
Install

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.

Clone the repo
git clone --depth 1 https://github.com/MarioEpkOne/PipelineIQ

Made for: Claude Code.

Or install pipelineiq, the plugin that ships this one along with the rest of its 10 commands, 6 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 spec-splitter

README.md
[![agentmods](https://agentmods.dev/badge/commands/marioepkone/pipelineiq/spec-splitter/github.svg)](https://agentmods.dev/commands/marioepkone/pipelineiq/spec-splitter)
Your own site
<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/spec-splitter"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/spec-splitter/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 spec-splitter

Your own site · 80×15
<a href="https://agentmods.dev/commands/marioepkone/pipelineiq/spec-splitter"><img src="https://agentmods.dev/badge/commands/marioepkone/pipelineiq/spec-splitter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,959 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.
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 $0.00000 $0.03959
Opus 5 $0.00000 $0.01980
Sonnet 5 $0.00000 $0.00792
Haiku 4.5 $0.00000 $0.00396

Measured 8d ago against content hash 6ce970765b62, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-splitter 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 8d 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.

commands/spec-splitter.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SPEC SPLITTER -- analyzes a spec for context window pressure, proposes a decomposition, and generates self-contained child specs optimized for parallel /pipeline-team execution.

Invocation: /spec-splitter $ARGUMENTS

The argument is the path to a spec file. If no argument provided, STOP: "Usage: /spec-splitter ".


Phase 1 -- Read and Analyze

Argument resolution

Resolve the argument as a file path relative to the project root.

  1. If the path exists as given -> use it.
  2. If not found -> check specs/<filename> as a fallback.
  3. If still not found -> check specs/team/<filename> as a fallback.
  4. If still not found -> STOP: "Spec file not found: [original-path]. Checked: [original-path], specs/[filename], specs/team/[filename]."

Re-split detection

After reading the spec, check for a **Split from**: line. If found, store the parent path for a warning in Phase 4 but do not stop yet.

Read and extract

Read the spec file in full. Before extracting, scan for the expected section headings (## Goal, ## Decisions, ## Technical Design, ## Edge Cases, ## Constraints, ## Current State, ## Open Questions). Report which were found and which are missing:

Sections found: Goal, Decisions, Technical Design, Edge Cases, Constraints, Current State
Sections missing: Open Questions (optional -- OK to proceed)

If a missing section has a near-match (e.g., ## Design instead of ## Technical Design, or ## Edge Cases & Error Handling instead of ## Edge Cases), flag it: "Found '## Design' -- did you mean '## Technical Design'? Treating as Technical Design." Use the near-match as the intended section.

Extract these components:

  1. Title -- first # heading
  2. Goal -- full text of Goal section
  3. Decisions -- all D1..DN entries, including rationale
  4. Technical Design -- full text, noting distinct subsections (each ### heading within Technical Design = one subsection)
  5. Edge Cases -- all rows from the table
  6. Constraints -- all items
  7. Current State -- full text
  8. Open Questions -- if present

Read the full file on GitHub · 366 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. 8d ago First seen · 366 lines · 0 tokens per session scan A 6ce970765b62

Subscribe to this mod's changes

spec-splitter is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,959 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 2026-08-31.