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 encode-repo-serenagit 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/encode-repo-serena)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/encode-repo-serena"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/encode-repo-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/rjmurillo/ai-agents/encode-repo-serena"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/encode-repo-serena.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 | $0.00097 | $0.01362 |
| Opus 5.5 | $0.00039 | $0.00545 |
| Sonnet 5.5 | $0.00019 | $0.00272 |
| Haiku 4.5 | $0.00010 | $0.00136 |
Grade A, and why
encode-repo-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 1mo 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Encode Repository (Serena-Enhanced)
Transform an undocumented codebase into a rich, searchable knowledge repository using Serena's LSP-powered symbol analysis.
Triggers
| Trigger Phrase | Operation |
|---|---|
encode this repository |
Full 12-phase encoding pipeline |
populate forgetful with this codebase |
Full encoding pipeline |
onboard to this repo |
Discovery + foundation phases |
refresh project understanding |
Re-run encoding on updated codebase |
build knowledge base for this project |
Full encoding pipeline |
When to Use
Use this skill when:
- Onboarding to a new repository that lacks Forgetful knowledge
- Repository structure has changed significantly since last encoding
- Forgetful searches return sparse or outdated results for the project
Use research-and-incorporate instead when:
- Researching an external topic, not encoding a codebase
- You need analysis of a single concept, not full repository encoding
Quick Start
/encode-repo-serena
/encode-repo-serena ./my-project
"encode this repository"
"populate forgetful with this codebase"
| Input | Output | Duration |
|---|---|---|
| Codebase path | Forgetful memories + entities + docs | 30-60 min |
Prerequisites
- Serena plugin:
claude plugins list | grep serena - Forgetful MCP: Test with
execute_forgetful_tool("list_projects", {}) - If missing, run
/context-hub-setupfirst
Process
Phase 0: Discovery
Assess project size, complexity, and structure. Produce a structure map.
Phase 1: Foundation
Create 5-10 project overview memories covering purpose, tech stack, and entry points.
Phase 1B: Dependencies
Create 1-3 dependency memories documenting external libraries and internal references.
Phase 2: Symbols
Use Serena find_symbol and find_referencing_symbols to produce 10-15 architecture memories.
Phase 2B: Entities
Create component entities with relationships in Forgetful. Deduplicate before creating.
What ships with it
3 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.
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.
- 1mo ago First seen · 185 lines · 97 tokens per session scan A d45ef5476c07
encode-repo-serena is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,362 once invoked, about $0.0004 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
context-engine
Loads and manages company context for all C-suite advisor skills. Reads /.claude/company-context.md, detects stale context (older than 90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks…
handoff
Create a structured session handoff when context is running low or work is pausing. Deep context mining, self-validation, multi-file splitting. Captures everything the next session needs.
abmind-runtime-operations
Inspect and maintain abmind memory, persona files, sleep, backups, encryption, and runtime health.
abmind_recall_workaround
Fallback when abmind recall / the abmindrecall tool fails — read memories directly from the SQLite DB.
memory-search
Search persistent memory for facts, decisions, and past conversations.
topic-save
Save and manage topic-specific knowledge files from conversations.