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/MarioEpkOne/PipelineIQWrote 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/marioepkone/pipelineiq/spec-splitter)<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.
<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>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 | $0.00000 | $0.03959 |
| Opus 5.5 | $0.00000 | $0.01584 |
| Sonnet 5.5 | $0.00000 | $0.00792 |
| Haiku 4.5 | $0.00000 | $0.00396 |
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 2mo 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 — 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.
- If the path exists as given -> use it.
- If not found -> check
specs/<filename>as a fallback. - If still not found -> check
specs/team/<filename>as a fallback. - 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:
- Title -- first
#heading - Goal -- full text of Goal section
- Decisions -- all D1..DN entries, including rationale
- Technical Design -- full text, noting distinct subsections (each
###heading within Technical Design = one subsection) - Edge Cases -- all rows from the table
- Constraints -- all items
- Current State -- full text
- Open Questions -- if present
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.
- 2mo ago First seen · 366 lines · 0 tokens per session scan A 6ce970765b62
spec-splitter is a command published in the GitHub repository MarioEpkOne/PipelineIQ (2 stars, last pushed 4mo 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.
Other commands, from other repositories
review-plan
Critically review the current plan/approach before implementing — assumptions, gaps, blast radius, deploy safety.
explain-dev
Write a WhatsApp-ready, non-technical message explaining a development to the client.
feature
Run the full feature pipeline — explore → plan → implement → review → test — for the change described in the argument.
triage
Triage a bug report (PDF / markdown / text) — extract the issues, prioritize, then run the fix pipeline per issue.
fix
Diagnose and fix a bug — reproduce → locate → root-cause → fix → test.
review
Review the current diff for bugs, security issues, and regressions.