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/krishnesh7/claude-usage-analytics/getting-startednpx skills add krishnesh7/claude-usage-analytics --skill getting-startedgit clone --depth 1 https://github.com/krishnesh7/claude-usage-analyticsWhat 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 | $0.00063 | $0.00718 |
| Opus 5 | $0.00032 | $0.00359 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade B, and why
getting-started scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/usage/stage_map.json How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-usage-tracker — New Project Setup
You are helping the user set up token/cost tracking for a new Claude Code project. Follow these steps in order, checking state before running commands.
Step 1 — Verify the tracker is installed
~/.claude/usage/parser/parse.mjs --version 2>/dev/null || \
ls ~/.claude/usage/usage.db 2>/dev/null && echo "DB exists" || echo "DB missing"
If the DB doesn't exist yet, run cu parse first.
Step 2 — Check if the project is already registered
${CLAUDE_PLUGIN_ROOT}/bin/cu project list
If the project already appears in the list, skip to Step 4.
Step 3 — Register the project
Ask the user for the project name if you don't already know it. Then run from the project's root directory:
cd <project-root>
${CLAUDE_PLUGIN_ROOT}/bin/cu project init <name>
Confirm registration succeeded — the output shows match_patterns that will
be used to link sessions.
Step 4 — Check stage mapping (optional but recommended)
cat ~/.claude/usage/stage_map.json
If the project's directory name is not in the mappings block, offer to add
it. Ask: "What SDLC stage are most sessions in this project?
(requirements / design / impl / test / deploy / explore / adhoc)"
When they answer, show them the line to add to stage_map.json.
Step 5 — Confirm session resolution
Run a quick confidence check on the current directory:
${CLAUDE_PLUGIN_ROOT}/bin/cu session-resolve --cwd "$(pwd)"
Explain the result:
EXACTorSUBDIR→ perfect, sessions will auto-tag silentlyFUZZY→ will work but might prompt occasionally; offer to tighten the patternUNMATCHED→ registration didn't take; check thatcu project listshows the project
Step 6 — Show quick-reference
Summarise the key commands they'll use day-to-day:
| What | How |
|---|---|
| See this week's spend | /usage in Claude Code |
| Check session assignment | /project-confirm |
| Regenerate CLAUDE_USAGE.md | /usage-doc |
| Full HTML report | /usage-report |
| Fix project tag mid-session | /project-confirm → follow prompts |
| Read the full guide | /usage-guide |
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 · 91 lines · 63 tokens per session scan B c100f67d4025
getting-started is a skill published in the GitHub repository krishnesh7/claude-usage-analytics (2 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 718 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after…
industry-chain
产业链下钻与不可替代性判定方法:以龙头为"需求入口"沿供应链逐层下钻(整机 / 龙头 → 部件 → 核心器件 → 材料 → 衬底与设备),用物理 / 材料约束(扩产周期、良率、认证周期、有无替代)当筛子找供给刚性的卡口;给每个标的贴不可替代性标签(techmoat / capacitymoat / both / 待补)并列证据;含"卡口越硬越贵"与预期差四问的校准。当任务涉及产业链位置、上下游、护城河、不可替代性、供给瓶颈、竞争格局时加载;单纯取数、估值计算、财报拆分等不涉及产业链结构的任务不要加载。只产出框架与证据表,不给投资动作建议。.
live-dashboard
Notion 风团队仪表板, KPI + 7 日 sparkline + activity feed + 任务表.
selecting-vizro-charts
Use this skill when choosing chart types, applying Plotly Express conventions, configuring colors, building KPI cards, or adding tables (AG Grid) to Vizro dashboards. Activate when the user asks which chart fits their data, needs custom chart functions, wants to set colors or palettes, is creating KPI metric cards, or…
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to…
catalyst-risk
催化剂与风险的反证式写法:每个强结论必须先找反证;催化剂按"兑现型 / 预期型 / 周期型"分类并要求可验证的数据时点;风险按技术路线断层、客户集中、产能过剩与价格战、周期顶、预期透支(假便宜 PEG)、一致预期下修、治理与流动性、数据源冲突分类;裁决点的标准写法(什么数据出来会改变判断 + 下一个公开数据时点);知识档案旧结论的反证处理。当任务涉及风险、反证、催化剂、裁决点、预期兑现、什么会推翻结论时加载;单纯取数、估值计算、财报拆分等不需要反证框架的任务不要加载。只产出框架、概率与裁决点,不给投资动作建议。.