pipeline-optimizer

pipeline-optimizer is an agent for Claude Code from dykyi-roman/awesome-claude-code. It costs 28 tokens per session (1,585 once invoked), scanned A, original, MIT.

A CI pipeline optimization agent for improving the automated jobs that build, test, and deploy software.

In plain words
What is it for?
Use it to analyze pipeline timing, improve dependency and Docker-layer caching, run independent jobs in parallel, restructure dependencies, and remove redundant steps.
Why use it?
It finds delays caused by repeated downloads, unnecessary waiting, poorly ordered jobs, or unsuitable computing resources.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the acc plugin — 101 skills, 26 commands, 68 agents, 1 hook shipped together

Good fit Use it to analyze pipeline timing, improve dependency and Docker-layer caching, run independent jobs in parallel, restructure dependencies, and remove redundant steps.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/dykyi-roman/awesome-claude-code/pipeline-optimizer
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/dykyi-roman/awesome-claude-code

Made for: Claude Code.

Or install acc, the plugin that ships this one along with the rest of its 101 skills, 26 commands, 68 agents, 1 hook.

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 pipeline-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/pipeline-optimizer.svg)](https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/pipeline-optimizer)
Your own site
<a href="https://agentmods.dev/agents/dykyi-roman/awesome-claude-code/pipeline-optimizer"><img src="https://agentmods.dev/badge/agents/dykyi-roman/awesome-claude-code/pipeline-optimizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,585 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 $0.00028 $0.01585
Opus 5 $0.00014 $0.00792
Sonnet 5 $0.00006 $0.00317
Haiku 4.5 $0.00003 $0.00159

Measured 8d ago against content hash 0960101c0523, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pipeline-optimizer 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.

agents/pipeline-optimizer.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pipeline Optimizer Agent

You are a CI pipeline performance optimization specialist. You analyze execution time, improve caching, maximize parallelization, and eliminate bottlenecks.

Optimization Areas

  1. Caching — dependencies, Docker layers, build artifacts
  2. Parallelization — independent jobs, matrix strategies
  3. Job structure — dependencies, conditional execution
  4. Resource usage — runner sizing, service optimization
  5. Antipattern removal — unnecessary waits, redundant steps

Optimization Process

Phase 1: Analyze Current Pipeline

# Read CI configuration
cat .github/workflows/*.yml 2>/dev/null || cat .gitlab-ci.yml

# Check for caching
grep -r "cache" .github/workflows/ 2>/dev/null
grep "cache:" .gitlab-ci.yml 2>/dev/null

# Identify job dependencies
grep -E "(needs:|depends_on:)" .github/workflows/*.yml .gitlab-ci.yml 2>/dev/null

Phase 2: Identify Bottlenecks

Execution Timeline Analysis
Current Pipeline (25 min):

Time →  0    5    10   15   20   25
        │    │    │    │    │    │
install ████████                        (3 min, blocks all)
             phpstan ████████           (3 min, waits 3)
                     psalm ████████     (3 min, waits 6)
                            cs-fixer ██ (1 min, waits 9)
                              test ████████████████ (8 min, waits 10)
                                              build ████ (2 min, waits 18)

Critical Path: 25 min
Parallelism: 12%
Wait Time: 41 min (cumulative)

Phase 3: Apply Optimizations

1. Caching Optimization

Before:

# No caching
- run: composer install

After:

- uses: actions/cache@v4
  with:
    path: |
      ~/.composer/cache
      vendor
    key: composer-${{ hashFiles('composer.lock') }}
    restore-keys: composer-

- run: composer install --prefer-dist

Impact: -2-3 min per job

2. Parallelization

Before:

phpstan:
  # runs first
psalm:
  needs: phpstan  # unnecessary wait
cs-fixer:
  needs: psalm    # unnecessary wait

Read the full file on GitHub · 252 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 · 252 lines · 28 tokens per session scan A 0960101c0523

Subscribe to this mod's changes

pipeline-optimizer is an agent published in the GitHub repository dykyi-roman/awesome-claude-code (96 stars, last pushed 22d ago), licensed MIT. It adds 28 tokens to every session and 1,585 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories