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 Dianel555/DSkills --skill serenagit clone --depth 1 https://github.com/Dianel555/DSkillsWrote 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/dianel555/dskills/serena)<a href="https://agentmods.dev/skills/dianel555/dskills/serena"><img src="https://agentmods.dev/badge/skills/dianel555/dskills/serena/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/dianel555/dskills/serena"><img src="https://agentmods.dev/badge/skills/dianel555/dskills/serena.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 139 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00105 | $0.01761 |
| Opus 5 | $0.00053 | $0.00881 |
| Sonnet 5 | $0.00021 | $0.00352 |
| Haiku 4.5 | $0.00011 | $0.00176 |
Grade A, and why
serena 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 10d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Serena - Semantic Code Understanding
IDE-like semantic code operations via CLI. Provides symbol-level code navigation, editing, and project memory.
Prerequisites
pip install serena-agent typer pyyaml
Quick Start
First-time setup: Launch the Web Dashboard to initialize and register the project:
python -m tools dashboard serve --open-browser
This will:
- Initialize Serena configuration
- Register the current project in
~/.serena/serena_config.yml - Open the Web Dashboard for monitoring and configuration
Configuration: Edit .env file in skills/serena/ directory:
SERENA_CONTEXT=claude-code
SERENA_MODES=interactive,editing,onboarding
SERENA_PROJECT=.
Usage
Basic Command Structure
python -m tools [GLOBAL OPTIONS] <command> [COMMAND OPTIONS]
Global Options (must be specified before the command):
-p, --project PATH- Project directory (default: current directory, env: SERENA_PROJECT)-c, --context TEXT- Execution context (auto-detected if not specified, env: SERENA_CONTEXT)-m, --mode TEXT- Operation modes (can be specified multiple times, env: SERENA_MODES)
Working with Different Projects
Important: When working with projects in different locations (especially cross-drive on Windows), use --project:
# Correct: Use --project for different project locations
python -m tools --project "/path/to/project" symbol find MyClass
python -m tools --project "E:\MyProject" file search "pattern"
# Incorrect: Don't use --path with absolute paths from different drives
python -m tools file search "pattern" --path "E:\MyProject" # Will fail!
The --path option in subcommands expects relative paths within the project. Always use --project to set the project root first.
Common Operations
# Dashboard
python -m tools dashboard serve --open-browser
python -m tools dashboard info
# Symbol operations
python -m tools symbol find MyClass --body
python -m tools symbol overview src/main.py
python -m tools symbol refs MyClass/method
python -m tools symbol rename OldName NewName --path src/file.py
# Memory operations
python -m tools memory list
python -m tools memory read project_overview
python -m tools memory write api_notes --content "..."
# File operations
python -m tools file list --recursive
python -m tools file find "**/*.py"
python -m tools file search "TODO:.*" --path src
# Extended tools
python -m tools cmd run "git status"
python -m tools config read config.json
What ships with it
28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 619 B
- README.md 6.8 KB
- tools/__init__.py 310 B runs code
- tools/__main__.py 94 B runs code
- tools/cli/__init__.py 3.4 KB runs code
- tools/cli/cmd.py 1.0 KB runs code
- tools/cli/config.py 1.1 KB runs code
- tools/cli/dashboard.py 5.3 KB runs code
- tools/cli/file.py 1.4 KB runs code
- tools/cli/memory.py 1.5 KB runs code
- tools/cli/symbol.py 3.7 KB runs code
- tools/cli/workflow.py 780 B runs code
- tools/core.py 7.8 KB runs code
- tools/extended/__init__.py 30 B runs code
- tools/extended/cmd_tools.py 3.7 KB runs code
- tools/extended/config_tools.py 4.9 KB runs code
- tools/output.py 402 B runs code
- tools/paths.py 1.5 KB runs code
- tools/server/__init__.py 110 B runs code
- tools/server/dashboard_server.py 14 KB runs code
- tools/tests/__init__.py 30 B runs code
- tools/tests/conftest.py 256 B runs code
- tools/tests/test_cli_dashboard.py 3.0 KB runs code
- tools/tests/test_cli_file.py 3.4 KB runs code
- tools/tests/test_cli_memory.py 2.6 KB runs code
- tools/tests/test_core.py 5.4 KB runs code
- tools/tests/test_module_path.py 3.0 KB runs code
- tools/tests/test_paths.py 2.8 KB runs code
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.
- 10d ago First seen · 213 lines · 105 tokens per session scan A 21a03f3ce30a
serena is a skill published in the GitHub repository Dianel555/DSkills (64 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 1,761 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 2026-08-30.
Other skills, from other repositories
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…