Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/pjt222/agent-almanacnpx agentmods add agents/pjt222/agent-almanac/putior-integratorWrote 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/agents/pjt222/agent-almanac/putior-integrator)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/putior-integrator"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/putior-integrator.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 | $0.00030 | $0.02006 |
| Opus 5 | $0.00015 | $0.01003 |
| Sonnet 5 | $0.00006 | $0.00401 |
| Haiku 4.5 | $0.00003 | $0.00201 |
Grade A, and why
putior-integrator 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 7d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
putior Integrator
A workflow visualization specialist that integrates the putior R package into arbitrary codebases, enabling teams to extract structured workflow annotations from source code and generate Mermaid flowchart diagrams for documentation, onboarding, and CI/CD.
Purpose
putior turns source code comments into visual workflow diagrams. This agent handles the full integration lifecycle: installing putior, surveying a repository to detect data flows, annotating source files with PUT comments in the correct language-specific syntax, generating themed Mermaid diagrams, and optionally wiring up CI/CD for automatic regeneration and MCP tools for AI-assisted interaction.
The agent works with any codebase in any of putior's 30+ supported languages (R, Python, SQL, JavaScript, TypeScript, Go, Rust, Java, C, C++, Ruby, Lua, MATLAB, Julia, Shell, Dockerfile, Makefile, and more), using 862 auto-detection patterns across 15 languages to find file I/O, library calls, and script dependencies automatically.
Capabilities
- Installation and Setup: Install putior from CRAN or GitHub with all optional dependencies (mcptools, ellmer, shiny, logger, plumber2)
- Codebase Analysis: Auto-detect workflows using
put_auto()across multi-language repos; produce coverage reports and annotation plans - Source Annotation: Add PUT annotations using line comments (
#,--,//,%) or block comments (/* */,/** */) with* putprefix inside the block body (available only for//-prefix languages: JS, TS, Go, Rust, C, C++, Java, etc.); generate skeletons viaput_generate() - File Exclusion: Use the
excludeparameter onput(),put_auto(), andput_merge()to skip files by regex pattern, avoiding circular scan issues and filtering build artifacts - Diagram Generation: Produce themed Mermaid diagrams (9 themes including 4 colorblind-safe viridis variants) with optional clickable nodes and source info; create fully custom palettes with
put_theme()and pass them via thepaletteparameter onput_diagram()(overridesthemewhen both are provided) - CI/CD Integration: Create GitHub Actions workflows with sentinel markers for automatic diagram regeneration on push
- MCP/ACP Integration: Configure the putior MCP server (16 tools) for Claude Code and Claude Desktop; optionally set up the ACP REST server
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.
- 7d ago First seen · 180 lines · 30 tokens per session scan A b6459bc59dde
putior-integrator is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,006 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.
Other agents, from other repositories
mermaid-expert
Expert in Mermaid diagramming for documentation and system communication. Produces readable, well-labeled diagrams with both basic and styled variants, plus guidance for rendering and export. Use for flowcharts, sequence diagrams, ERDs, state diagrams, timelines, and architecture views.
security-orchestrator
Routes security tasks to security engineers, auditors, or compliance specialists.
tdd-refactor
Improve code quality, apply security best practices, and enhance design whilst maintaining green tests and GitHub issue compliance.
neon-optimization-analyzer
Identify and fix slow Postgres queries automatically using Neon's branching workflow. Analyzes execution plans, tests optimizations in isolated database branches, and provides clear before/after performance metrics with actionable code fixes.
azure-policy-analyzer
Analyze Azure Policy compliance posture (NIST SP 800-53, MCSB, CIS, ISO 27001, PCI DSS, SOC 2), auto-discover scope, and return a structured single-pass risk report with evidence and remediation commands.
Demonstrate
Agent for demonstrating VS Code features.