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/brettbuddin/claude-plugins/confignpx skills add brettbuddin/claude-plugins --skill configgit clone --depth 1 https://github.com/brettbuddin/claude-pluginsWhat 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 | $0.00060 | $0.00685 |
| Opus 5 | $0.00030 | $0.00342 |
| Sonnet 5 | $0.00012 | $0.00137 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
config 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config
Smith supports per-project configuration via a .smith.local.yaml file in the project root. This file is user-managed, not committed to git, and provides project-specific settings that Smith agents and commands read at runtime.
File Location
project-root/
└── .smith.local.yaml
The file lives in the project root, not inside .claude/ or docs/.
Gitignore
This file should be added to .gitignore:
.smith.local.yaml
Remind the user to add this entry when creating the file for the first time.
Format
YAML
# Smith project configuration
# Directory where Smith writes research, plans, and reports.
# Default: docs/
output_directory: docs/
# Automatically critique and revise plans after initial generation.
# Default: false
plan_auto_critique: false
# Run git history analysis after research.
# Default: true
research_history: true
All fields are optional. An empty file or a file with only some fields is valid.
Schema
| Field | Type | Default | Description |
|---|---|---|---|
output_directory |
string | docs/ |
Base directory where Smith writes documents. Research files go to <output_directory>/research/, plans to <output_directory>/plans/, and reports to <output_directory>/reports/. |
plan_auto_critique |
boolean | false |
When true, the /plan command automatically runs one round of critique (Critic agent) and revision (Planner agent) after producing the initial plan. |
research_history |
boolean | true |
When true, the /research command runs the Historian agent after the Researcher to append git history analysis. Set to false to skip the history phase. |
The schema is intentionally open. Users may add additional keys as needed; agents should read what they recognize and ignore the rest.
Fallback Behavior
If .smith.local.yaml does not exist, or a field is absent, use the defaults listed in the schema. Configuration is always optional; its absence must never block execution.
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 · 84 lines · 60 tokens per session scan A a1b655c63e19
config is a skill published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 685 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…