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 agentmods add skills/anilcancakir/claude-code-plugins/serena-memorynpx skills add anilcancakir/claude-code-plugins --skill serena-memorygit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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/anilcancakir/claude-code-plugins/serena-memory)<a href="https://agentmods.dev/skills/anilcancakir/claude-code-plugins/serena-memory"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code-plugins/serena-memory.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 | $0.00057 | $0.00463 |
| Opus 5 | $0.00028 | $0.00231 |
| Sonnet 5 | $0.00011 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
serena-memory 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.
What it actually says
Serena Memory Management
Memory Operations
| Operation | Tool |
|---|---|
| Save knowledge | write_memory(key, content) |
| Update existing | edit_memory(key, content) |
| Load knowledge | read_memory(key) |
| List all | list_memories() |
| Remove | delete_memory(key) |
Recommended Memory Keys
| Key | Purpose |
|---|---|
architecture_overview |
System architecture |
code_conventions |
Coding standards |
recent_changes |
Latest commits |
known_issues |
Bugs and workarounds |
test_patterns |
Testing conventions |
session_context |
Current task (preserved during compaction) |
When to Update Memories
- After exploration: Save architectural insights
- After debugging: Document root causes and fixes
- After refactoring: Record successful patterns
- Before compaction: Preserve current task context
- After commits: Summarize significant changes
Example: Architecture Memory
write_memory(
key="architecture_overview",
content="""
# Project Architecture
## Layers
- API: FastAPI routes in src/api/
- Services: Business logic in src/services/
- Models: SQLAlchemy models in src/models/
## Key Patterns
- Dependency injection via FastAPI Depends
- Repository pattern for data access
## Entry Points
- Main app: src/main.py
- CLI: src/cli.py
"""
)
Example: Code Conventions Memory
write_memory(
key="code_conventions",
content="""
# Code Conventions
- snake_case for functions/variables
- PascalCase for classes
- Type hints required for public functions
- Docstrings in Google style
- Tests in tests/ mirror src/ structure
"""
)
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 · 81 lines · 57 tokens per session scan A d5faea61f37d
serena-memory is a skill published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 57 tokens to every session and 463 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
system-boot
Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
evolution-guide
Explains how Evolving Lite works when the user asks about the system, its features, or how to use it. Triggers on questions like "how does this work", "what is evolving lite", "what hooks are running", "explain the system".
claude-code-session-broker
Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.
arcgentic
Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
verify-gates
Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…