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 skills add thedavidweng/skills --skill cli-invoicegit clone --depth 1 https://github.com/thedavidweng/skillsWrote 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/thedavidweng/skills/cli-invoice)<a href="https://agentmods.dev/skills/thedavidweng/skills/cli-invoice"><img src="https://agentmods.dev/badge/skills/thedavidweng/skills/cli-invoice/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thedavidweng/skills/cli-invoice"><img src="https://agentmods.dev/badge/skills/thedavidweng/skills/cli-invoice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00037 | $0.00360 |
| Opus 5.5 | $0.00015 | $0.00144 |
| Sonnet 5.5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
cli-invoice 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 1mo 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
The command IS the source. Store each invoice's command in your notes (one fenced block per invoice); regenerate on demand. Never persist PDFs. Needs the invoice CLI (brew install invoice).
invoice generate --from "Name" --to "Client" \
--id "2026-001" --date "Mar 31, 2026" --due "Apr 14, 2026" \
--item "Work" --quantity 40 --rate 75 [--tax 0.05] \
[--note "E-transfer to [email protected]"] [--output a.pdf]
Repeat --item/--quantity/--rate once per line item. --import file.json takes parallel arrays (items/quantities/rates), not objects.
Pin --id, --date, --due. They default to today's date, so an unpinned command regenerates a different invoice. Always pass --from/--to: the defaults are placeholder company names. The CLI reads no environment variables.
Don't: floats in --quantity (the tool fails with strconv.Atoi; scale first: qty×10^d as an int, rate/10^d, then check the total); percentages for tax/discount (use decimals, 0.05); separate payment sections (embed in --note, since per-client payment details differ).
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.
- 1mo ago Changed · +3 lines · +7 tokens per session c7e6d4991421
- 1mo ago Changed · -169 lines · -40 tokens per session 6f0c2cb7293f
- 2mo ago First seen · 186 lines · 70 tokens per session scan A 0185cdaa9c66
cli-invoice is a skill published in the GitHub repository thedavidweng/skills (11 stars, last pushed 8d ago), licensed MIT. It adds 37 tokens to every session and 360 once invoked, about $0.0001 per session on Opus 5.5. 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.
cli-invoice compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cli-invoicethedavidweng/skills | Skill | 11 | 8d ago | MIT | A | 37 | Claude Code, Codex |
| invoicenexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 46 | Claude Code, Codex |
| report-generatoryennanliu/InvestSkill | Skill | 275 | 13d ago | MIT | A | 11 | Claude Code |
| cwicr-report-generatordatadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction | Skill | 394 | 18d ago | MIT | A | 29 | Claude Code, Codex |
| iflytek-ocr-invoiceiflytek/iFly-Skills | Skill | 213 | 3d ago | Apache-2.0 | A | 77 | Claude Code, Codex |
| financial-parserOneWave-AI/claude-skills | Skill | 415 | 18d ago | MIT | A | 41 | Claude Code, Codex |
| billing-automationTerminalSkills/skills | Skill | 192 | yesterday | Apache-2.0 | A | 86 | Claude Code, Codex |