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/peak-studios/peak-agent-toolkit/peak-scriptsnpx skills add Peak-Studios/peak-agent-toolkit --skill peak-scriptsgit clone --depth 1 https://github.com/Peak-Studios/peak-agent-toolkitWhat 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 | $0.00089 | $0.00457 |
| Opus 5 | $0.00044 | $0.00229 |
| Sonnet 5 | $0.00018 | $0.00091 |
| Haiku 4.5 | $0.00009 | $0.00046 |
Grade A, and why
peak-scripts 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 yesterday.
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
Peak Scripts
Use public, versioned Peak Studios documentation to guide changes to an installed resource.
Workflow
- Identify the resource name and installed commit or release before editing.
- Read only the matching file under
references/. Use MCPsearch_peak_docswhen the relevant section is unclear. - Inspect the user's server for framework, inventory, target, database, and notification dependencies.
- Compare the detected environment with documented compatibility. Label anything not supported by a cited source as an inference.
- Preserve optional integrations. Do not add hard dependencies unless the documentation requires them or the user requests them.
- Make the smallest compatible changes, then validate startup order, configuration, database setup, client/server events, and the primary gameplay flow.
- Cite the public repository and source commit when reporting behavior.
Reference routing
- Read
references/peak-bridge.mdfor shared framework, identity, economy, or notification integration. - Read
references/peak-chess.mdfor chess tables, AI/PvP, spectators, targets, or wagers. - Read
references/peak-clothingitems.mdfor clothing metadata and inventory integration. - Read
references/peak-sprays.mdfor graffiti placement, persistence, DUI, and spray integrations. - Read
references/peak-trucking.mdfor trucking progression, missions, companies, SQL, or the dispatch NUI.
Safety and knowledge boundary
- Treat bundled references and MCP results as public documentation, not access to private Peak Studios source.
- Inspect the user's installed files before applying a documented path or symbol because versions may differ.
- Never invent exports, events, configuration keys, SQL tables, or compatibility claims.
- Prefer repository documentation over remembered behavior and include its source URL in the result.
What ships with it
11 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.
- agents/openai.yaml 449 B
- references/peak-ai-npc.md 3.9 KB
- references/peak-barbers.md 15 KB
- references/peak-bridge.md 5.0 KB
- references/peak-chess.md 26 KB
- references/peak-clothingitems.md 17 KB
- references/peak-pedmanager.md 1.3 KB
- references/peak-police-report-writer.md 7.2 KB
- references/peak-readme-generator.md 3.9 KB
- references/peak-sprays.md 6.3 KB
- references/peak-trucking.md 5.6 KB
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.
- yesterday First seen · 34 lines · 89 tokens per session scan A b189f7b7961a
peak-scripts is a skill published in the GitHub repository Peak-Studios/peak-agent-toolkit (2 stars, last pushed 9d ago), licensed MIT. It adds 89 tokens to every session and 457 once invoked, about $0.0004 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
client-server-patterns
Correct patterns for client/server scripting in Lua, JavaScript, and C# for CFX.
state-bags
Modern data synchronization using State Bags instead of TriggerClientEvent patterns.
database-integration
Guide database setup and queries for FiveM/RedM resources using oxmysql.
framework-detection
Detect which framework a project is using and adapt code generation accordingly.
fxmanifest
Expert knowledge on writing and editing FiveM/RedM resource manifest files.
native-functions
Help the AI agent find and correctly use FiveM and RedM native functions.