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 using-serena-symbolsgit 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/using-serena-symbols)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/using-serena-symbols"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/using-serena-symbols/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/using-serena-symbols"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/using-serena-symbols.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00066 | $0.02110 |
| Opus 5.5 | $0.00026 | $0.00844 |
| Sonnet 5.5 | $0.00013 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
using-serena-symbols 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Serena Symbol Analysis
Serena provides LSP-powered code intelligence for accurate symbol extraction, relationship discovery, and cross-file analysis.
When to Use Serena vs Text Search
| Use Serena | Use Grep/Text Search |
|---|---|
| Finding class/function definitions | Searching for string literals |
| Tracing method references | Finding patterns in comments |
| Understanding call hierarchies | Searching config files |
| Analyzing imports/dependencies | Finding TODO/FIXME markers |
| Cross-file architecture analysis | Simple keyword search |
Key advantage: Serena understands code structure. find_symbol("UserService") finds the actual class definition, not every mention of "UserService" in comments or strings.
Core Tools
1. get_symbols_overview
Get high-level view of symbols in a file. Start here when exploring a new file.
mcp__plugin_serena_serena__get_symbols_overview(
{
"relative_path": "src/services/auth.py",
"depth": 1, # 0=top-level only, 1=include methods
}
)
Returns: Classes, functions, variables with their kind and location.
2. find_symbol
Find symbols by name pattern. Supports flexible matching.
Name path patterns:
UserService- Find any symbol named "UserService"UserService/authenticate- Find method in class/UserService- Exact match (absolute path)Servicewithsubstring_matching: true- Matches "UserService", "AuthService", etc.
mcp__plugin_serena_serena__find_symbol(
{
"name_path_pattern": "UserService/authenticate",
"include_body": true, # Get source code
"depth": 0, # 0=just this symbol, 1=include children
}
)
Key parameters:
include_body(bool): Include source code (use judiciously for context)depth(int): How many levels of children to retrieverelative_path(str): Restrict search to file/directorysubstring_matching(bool): Partial name matching
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.
- 6d ago Changed · -7 lines d23aec0ef6f7
- 9d ago Changed 43b0aaeee7a9
- 20d ago Changed · +12 lines d3af01019f96
- 22d ago Changed · +5 lines 6d579ece2a15
- 1mo ago Changed · -5 lines · -32 tokens per session 5494fcd5aac8
- 1mo ago First seen · 282 lines · 98 tokens per session scan A 28a9499ea305
using-serena-symbols is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 2,110 once invoked, about $0.0003 per session on Opus 5.5. 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
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.