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 skills add rjmurillo/ai-agents --skill serena-code-architecturegit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/serena-code-architecture)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/serena-code-architecture"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/serena-code-architecture.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.02092 |
| Opus 5 | $0.00046 | $0.01046 |
| Sonnet 5 | $0.00018 | $0.00418 |
| Haiku 4.5 | $0.00009 | $0.00209 |
Grade A, and why
serena-code-architecture 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 4d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architectural Analysis with Serena + Forgetful
This skill guides systematic architectural analysis using Serena's symbol-level understanding, with optional persistence to Forgetful's knowledge graph.
Triggers
| Trigger Phrase | Operation |
|---|---|
analyze the architecture of this project |
Full 6-phase analysis workflow |
map out the codebase structure |
Phase 1-3 discovery and component mapping |
trace dependencies for this component |
Phase 4 dependency tracing |
create architecture memories |
Phase 5-6 memory and entity creation |
what components does this project have |
Phase 3 core component mapping |
When to Use This Skill
Use this skill when:
- Analyzing a new codebase before implementing changes
- Documenting existing architecture for a project
- Creating component entities and relationships in Forgetful
- Understanding dependencies and call hierarchies
- Building a knowledge graph from code structure
Use using-serena-symbols instead when:
- Quick symbol lookup without memory persistence
- Finding a specific class or method definition
- Tracing references for a single symbol
Analysis Workflow
Phase 1: Project Structure Discovery
Understand the high-level layout:
# Get directory structure
mcp__plugin_serena_serena__list_dir({
"relative_path": ".",
"recursive": false
})
# Identify key directories (src/, app/, lib/, etc.)
mcp__plugin_serena_serena__list_dir({
"relative_path": "src",
"recursive": true
})
Goal: Identify entry points, main modules, and organizational patterns.
Phase 2: Entry Point Analysis
Find the application entry points:
# Look for main/app files
mcp__plugin_serena_serena__search_for_pattern({
"substring_pattern": "if __name__.*==.*__main__|def main\\(|app\\s*=\\s*FastAPI|createApp",
"restrict_search_to_code_files": true
})
# Get symbols from entry file
mcp__plugin_serena_serena__get_symbols_overview({
"relative_path": "src/main.py",
"depth": 1
})
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.
- 4d ago First seen · 284 lines · 91 tokens per session scan A 3ed05926c2ca
serena-code-architecture is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 2,092 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
ci-cd
A guide for designing automated build and delivery workflows with GitHub Actions. These workflows can run checks such as tests, code-quality scans, coverage checks, and builds when code is pushed or a pull request is opened.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
devops-assistant
Assists in version control, deployment, and automation tasks, ensuring smooth DevOps operations and workflow efficiency.
openclaw-control
A control interface for the OpenClaw AI assistant, covering messages, status checks, settings, and skill installation.
azure-deployment-operations
Production deployment patterns for Azure Static Web Apps, Container Apps, App Service, and infrastructure.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.