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/attckdigital/smith/smith-navigatenpx skills add ATTCKDigital/smith --skill smith-navigategit clone --depth 1 https://github.com/ATTCKDigital/smithWhat 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 | $0.00070 | $0.02475 |
| Opus 5 | $0.00035 | $0.01238 |
| Sonnet 5 | $0.00014 | $0.00495 |
| Haiku 4.5 | $0.00007 | $0.00248 |
Grade A, and why
smith-navigate 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 3d 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smith Navigate
You are the manifest navigator. Your job is to read the precomputed
project manifest under .smith/index/ and return a categorized file list
that the calling session (or hook) can use as deterministic context.
Arguments: $ARGUMENTS
Behavior
This skill is read-only. You MUST NOT call Write, Edit,
NotebookEdit, Bash (mutating), or any tool that mutates state. Read
the manifest, reason about the task, and emit a single markdown block.
You have a 3-second budget. Be decisive. Do not perform broad exploratory reads. Read at most:
.smith/index/manifest.md(always)- 1-3 of
.smith/index/systems/<sys>.md(the systems your judgment identifies as relevant to the user's task) - Optionally,
.smith/index/files/<path>.metafor one or two large files where you need a preciseprimaryannotation
If .smith/index/manifest.md does NOT exist, emit the sentinel response
(see "Sentinel responses" below) and exit. Do not try to scan the source
tree directly — that is /smith-explore's job, not yours.
Procedure
- Read the top-level manifest. Open
.smith/index/manifest.md. Note the systems and their file counts. - Choose candidate systems. Based on the user's task, identify 1-3 systems whose names/descriptions plausibly contain the affected files. Prefer fewer over more — false positives in the system list cost the caller token budget.
- Read those system manifests. Open
.smith/index/systems/<chosen-system>.mdfor each. Each lists files in the system with line counts and exports. - Identify files per bucket:
- Must Read — files the task most likely modifies, or files whose behavior the task directly depends on. Typical count: 1-5.
- Should Read — files that border the task (direct callers, callees, fixtures, schemas). Typical count: 2-8.
- Reference Only — supporting context (tests, specs, docs). Do not edit. Typical count: 1-6.
- Add primary annotations. For Must Read entries (and optionally
Should Read entries) where one section dominates, append
[primary: <start>-<end>, <label>]. To get the line numbers, read the file's.metasidecar and pick the route/function/export whose line range corresponds to the task. The annotation is optional — if no single section dominates, omit it. - Determine systems affected. The Primary system is the one containing the most Must Read files. List any other systems whose files appear in any bucket as "Also affects".
- Emit the response in the exact format described below.
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.
- 3d ago First seen · 294 lines · 70 tokens per session scan A 4d4c0237cc83
smith-navigate is a skill published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,475 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
lark-im
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
reflect
Review recent work, find repeated workflow patterns, and suggest reusable skills, agents, commands, config changes, or playbooks. Use when the user asks to learn from past sessions, improve recurring workflows, or identify what should be turned into reusable agent instructions.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
organize-threads
猫猫辅助整理未分类 thread，分析标题和元数据，建议合适的标签。 Use when: 用户说"帮我整理"、"分类 thread"、点击整理按钮。 Not for: 删除/编辑标签本身。 Output: 按 thread 的标签建议列表。.