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 skills/mkonstan/llm-tools/pipeline-buildernpx skills add mkonstan/llm-tools --skill pipeline-buildergit clone --depth 1 https://github.com/mkonstan/llm-toolsWrote 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/mkonstan/llm-tools/pipeline-builder)<a href="https://agentmods.dev/skills/mkonstan/llm-tools/pipeline-builder"><img src="https://agentmods.dev/badge/skills/mkonstan/llm-tools/pipeline-builder.svg" alt="Measured on agentmods" 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 | $0.00182 | $0.03538 |
| Opus 5 | $0.00091 | $0.01769 |
| Sonnet 5 | $0.00036 | $0.00708 |
| Haiku 4.5 | $0.00018 | $0.00354 |
Grade A, and why
pipeline-builder 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 5d 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline Builder
Execution model: Human-in-the-loop. Claude facilitates the discussion and generates artifacts; the human confirms, corrects, and approves at every gate.
Convert workflow documents into agentic pipeline skills that Claude Code and Cowork execute as enforced task lists.
Why Pipelines Beat Rules
Rules in a document are suggestions. Claude reads them, understands them, then optimizes for speed over process. The stronger the time pressure, the more rules get skipped.
Pipelines enforce rules through structure: each phase is a Task tool agent with a single job. Each agent writes output to a file. The next agent requires that file as input. You cannot skip Phase 2 because Phase 3 needs Phase 2's output file to exist.
Gates are verification agents that check the prior agent's work before the next phase fires. If the gate fails, work goes back — not forward. "Write tests first" stops being a suggestion and becomes a hard dependency.
Before Starting
Read these references when needed during the pipeline build:
references/interrogation_guide.md— How to probe the user's workflow for gaps, contradictions, and missing failure modesreferences/pipeline_patterns.md— Dispatcher patterns, agent prompt templates, gate templates, file handoff conventionsreferences/example_output.md— Complete worked example: CLAUDE.md rules → installed pipeline skill
The Pipeline (Follow This Task List)
This skill itself runs as a pipeline. Follow each task in order. Do not skip tasks. Do not combine tasks.
Task 1: INGEST
Ingest whatever the user provides — workflow document, verbal description, existing pipeline, process notes, or any combination. Adapt to each resource according to your understanding.
Action:
- Read the actual source artifacts — not summaries, not descriptions of files. If the user points to a file, read it. Summaries omit the details where gaps hide.
- List every rule, checkpoint, phase, and constraint you find
- Tag each item using whichever tags apply:
[phase]— a step in the workflow that produces an artifact[gate]— a verification/quality check[rule]— a behavioral constraint[working]— functioning as intended (for existing pipelines)[broken]— where a known failure lives (for existing pipelines)[suspect]— adjacent to a failure, may need to change (for existing pipelines)[unclear]— needs clarification
What ships with it
3 files 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.
- 5d ago First seen · 305 lines · 182 tokens per session scan A 259bf91759be
pipeline-builder is a skill published in the GitHub repository mkonstan/llm-tools (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 182 tokens to every session and 3,538 once invoked, about $0.0009 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…