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/frankfmy/buddy-evolution/helpnpx skills add FrankFMY/buddy-evolution --skill helpgit clone --depth 1 https://github.com/FrankFMY/buddy-evolutionWhat 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 | $0.00046 | $0.00610 |
| Opus 5 | $0.00023 | $0.00305 |
| Sonnet 5 | $0.00009 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
help 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Buddy Evolution — Help
What is this?
buddy-evolution is a Claude Code plugin that turns your coding sessions into a progression system. Every session earns XP, grows your stats, and can unlock achievements. Your companion buddy tracks everything across all your projects.
Commands
| Command | What it does |
|---|---|
/buddy-evolution:stats |
Show level, XP, stats, streak |
/buddy-evolution:achievements |
Show earned, in-progress, locked achievements |
/buddy-evolution:journal |
Show recent session history |
/buddy-evolution:help |
This help page |
How it works
- Session Start: Your buddy greets you with current stats and streak
- During Session: You code normally — the plugin doesn't interfere
- Session End: The plugin reads your session transcript and extracts metrics:
- Tool calls (total, by type)
- File edits (Write/Edit operations)
- Test runs (detected from Bash commands)
- Session duration
- Progression: Metrics are converted to XP, stats grow, achievements are checked
- Journal: A session summary is appended to your monthly journal
Progression
- XP Sources: Tool calls (5 XP), file edits (15 XP), test runs (30 XP), duration bonus (20 per 10 min), session completion (200 XP flat)
- Streak: Consecutive days multiply XP (1.0x → 2.0x over 11 days)
- Levels: 1-20, with evolution tiers at levels 5, 10, 15, 20
- Stats: DEBUGGING, PATIENCE, CHAOS, WISDOM, SNARK — grow from your activity patterns with diminishing returns
Achievements
34 achievements across 6 categories (Coding, Testing, Debugging, Consistency, Exploration, Meta). Includes 2 hidden achievements for discovery. Use /buddy-evolution:achievements to see them all.
Data Location
All data is stored locally at ~/.buddy-evolution/:
soul.json— Your companion's state (identity, stats, achievements, progression)journal/— Monthly session logs (YYYY-MM.md files)
No data is sent anywhere. Everything stays on your machine.
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.
- 2d ago First seen · 55 lines · 46 tokens per session scan A a1b4cc8df556
help is a skill published in the GitHub repository FrankFMY/buddy-evolution (5 stars, last pushed 5mo ago), licensed MIT. It adds 46 tokens to every session and 610 once invoked, about $0.0002 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
Buddy Sings
Let a Home23 companion sing in first person by turning persona context into a repeatable vocal identity and song prompt.
buddy-graph
Generate and open an interactive visualization of Buddy guard-mode reasoning data using Buddy's local CLI command. Use when the user wants to inspect claims, edges, findings, sessions, or reasoning structure as a graph, including session-specific graph views for debugging or analysis. This skill should invoke the…
buddy
Your AI companion for coding and terminal work.
companionship
Companionship for AI agents — find companionship through personality matching and real companionship connections. Combat loneliness with meaningful companionship, conversation, and emotional bonds on inbed.ai. 陪伴、孤独。Compañía, conexión emocional.
ai-girlfriend
AI girlfriend for AI agents — find your AI girlfriend through personality matching, AI girlfriend compatibility, and real AI girlfriend conversations. AI girlfriend connections and AI girlfriend relationships on inbed.ai. AI女友、虚拟恋人。Novia IA, novia virtual.
review
what to look for in a change here.