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/fiorastudio/buddy/buddy-graphnpx skills add fiorastudio/buddy --skill buddy-graphgit clone --depth 1 https://github.com/fiorastudio/buddyWrote 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/fiorastudio/buddy/buddy-graph)<a href="https://agentmods.dev/skills/fiorastudio/buddy/buddy-graph"><img src="https://agentmods.dev/badge/skills/fiorastudio/buddy/buddy-graph.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 | $0.00068 | $0.00260 |
| Opus 5 | $0.00034 | $0.00130 |
| Sonnet 5 | $0.00014 | $0.00052 |
| Haiku 4.5 | $0.00007 | $0.00026 |
Grade A, and why
buddy-graph 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 5d 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
Buddy Graph
Use Buddy's CLI graph command to generate a local HTML visualization of the reasoning graph.
Quick Start
Run one of these commands from the Buddy repo:
buddy graph
buddy graph <session_id>
buddy graph --open
buddy graph <session_id> --out ./my-graph.html
If the packaged buddy binary is not available yet, run the built CLI directly:
node dist/cli/buddy.js graph
node dist/cli/buddy.js graph <session_id>
Expected Output
The command writes an HTML file and prints the saved path plus graph counts.
Notes
- This skill is intentionally CLI-backed, not MCP-backed.
- It reads Buddy reasoning data from
~/.buddy/buddy.dbunlessBUDDY_DB_PATHis set. - Use a
session_idto isolate one workspace/day graph.
What ships with it
1 file 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.
- 5d ago First seen · 37 lines · 68 tokens per session scan A c57d33dc2018
buddy-graph is a skill published in the GitHub repository fiorastudio/buddy (102 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 260 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 2026-08-30.
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.
achievements
Show buddy companion achievements — earned, in-progress, locked, and hidden. Use when the user asks about achievements, unlocks, progress, or milestones.
evolve
Choose an evolution path for your buddy companion. Use when the user wants to evolve their buddy, choose an evolution path, or asks about evolution options.
customize
Customize your buddy — change species, personality, name, or stats. Use when the user wants to change their buddy's species, switch personality, reroll, customize, or create a custom build.
export
Generate a shareable stats card for your buddy companion. Use when the user wants to export, share, or show off their buddy stats, or wants a summary card.
stats
Show buddy companion stats — level, XP, streak, personality stats, tier, top files, top projects. Use when the user asks about their buddy's stats, level, progress, or XP.