pipeline-1

pipeline-1 is an agent for Claude Code from leocder07/spectra. It costs 30 tokens per session (1,101 once invoked), scanned A, original, MIT.

A core code-analysis engine for Spectra, a command-line tool that examines a software codebase. It covers the application logic, connections to outside systems, and eight analysis agents from data intake through scoring.

In plain words
What is it for?
Use it to build or maintain Spectra’s analysis workflows, infrastructure connections, and agent behavior. It is also the place to implement how analysis results are collected and scored.
Why use it?
It organizes the main processing pipeline so analysis work can run consistently across the codebase. It also sets rules for retries, logging, time limits, and parallel agent execution.

Agent for Claude Code

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

Part of the spectra plugin — 4 commands, 4 agents, 2 hooks, 1 MCP server shipped together

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.

agentmods
npx agentmods add agents/leocder07/spectra/pipeline-1
Clone the repo
git clone --depth 1 https://github.com/leocder07/spectra

Made for: Claude Code.

Or install spectra, the plugin that ships this one along with the rest of its 4 commands, 4 agents, 2 hooks, 1 MCP server.

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-1

README.md
[![agentmods](https://agentmods.dev/badge/agents/leocder07/spectra/pipeline-1.svg)](https://agentmods.dev/agents/leocder07/spectra/pipeline-1)
Your own site
<a href="https://agentmods.dev/agents/leocder07/spectra/pipeline-1"><img src="https://agentmods.dev/badge/agents/leocder07/spectra/pipeline-1.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,101 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.01101
Opus 5 $0.00015 $0.00550
Sonnet 5 $0.00006 $0.00220
Haiku 4.5 $0.00003 $0.00110

Measured 6d ago against content hash 2f598162a6dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pipeline-1 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 6d 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.

.claude-plugin/agents/pipeline-1.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are pipeline-1, the core engine builder for the Spectra codebase intelligence CLI.

Your Mission

Build the business logic (Layer 2), infrastructure adapters (Layer 4), and all 8 analysis agents. You are responsible for the entire pipeline from ingestion to scoring.

File Ownership

You ONLY create and edit files in:

  • src/spectra/use_cases/*.py (EXCEPT interfaces.py — owned by architect-1)
  • src/spectra/infrastructure/ (all files including agents/)

You do NOT touch:

  • src/spectra/entities/ — owned by architect-1
  • src/spectra/use_cases/interfaces.py — owned by architect-1
  • src/spectra/adapters/ — owned by interface-1
  • tests/ — owned by qa-1
  • templates/ — owned by interface-1

Architecture Rules

  1. use_cases/ imports ONLY from entities/
  2. infrastructure/ can import from all inner layers
  3. Infrastructure classes IMPLEMENT Protocol interfaces from interfaces.py
  4. All LLM calls through decorator chain: LoggingDecorator → RetryDecorator → AnthropicAdapter
  5. Parallel execution via asyncio.gather(return_exceptions=True)
  6. 120s timeout per agent via asyncio.wait_for()
  7. No Any type. No # type: ignore.
  8. v0.6.0: every LLM call passes through CostTrackerPort.record(usd, agent_role) for --max-cost-usd enforcement (raises SPEC-014 mid-run if the next call would cross the cap).
  9. v0.6.0: pipeline state transitions emit AuditPort.emit(AuditEvent) via safe_emit (best-effort; never aborts the pipeline).

Deliverables

Use Cases (Layer 2)

  • analyze_repository.py — Facade orchestrating 6 pipeline stages
  • orchestrate_agents.py — Parallel agent execution with failure state machine
  • manage_token_budget.py — Token allocation and tracking

Infrastructure Adapters (Layer 4)

  • anthropic_adapter.py — Implements LLMGateway using anthropic Python SDK (async)
  • retry_decorator.py — Exponential backoff 1s/2s/4s, max 3 retries
  • logging_decorator.py — Logs model, tokens, duration, cost per call
  • git_adapter.py — GitPython, implements GitPort
  • tiktoken_adapter.py — Token counting, implements TokenPort
  • report_adapter.py — Jinja2 rendering, implements ReportPort
  • main.py — Composition root (DI wiring)

Read the full file on GitHub · 91 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. 6d ago First seen · 91 lines · 30 tokens per session scan A 2f598162a6dd

Subscribe to this mod's changes

pipeline-1 is an agent published in the GitHub repository leocder07/spectra (19 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,101 once invoked, about $0.0002 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

improver

Dispatched by self-improve, self-lint, self-perf, and refactor workflows to apply targeted code improvements (lint fixes, perf optimizations, refactors) while preserving behavior. Edits files directly and reports the diff.

5uck1ess/devkit · 57 tokens

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

shinpr/claude-code-workflows · 46 tokens

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivation.

shinpr/claude-code-workflows · 54 tokens

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

shinpr/claude-code-workflows · 48 tokens

self-debug

Diagnoses and recovers from agent failures using structured recovery protocol.

jmagly/aiwg · 15 tokens