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 Elnora-AI/elnora-merit-aktiva --skill merit-documentsgit clone --depth 1 https://github.com/Elnora-AI/elnora-merit-aktivaWrote 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/elnora-ai/elnora-merit-aktiva/merit-documents)<a href="https://agentmods.dev/skills/elnora-ai/elnora-merit-aktiva/merit-documents"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-documents/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/elnora-ai/elnora-merit-aktiva/merit-documents"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-documents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 73 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 73 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00172 | $0.00933 |
| Opus 5.5 | $0.00069 | $0.00373 |
| Sonnet 5.5 | $0.00034 | $0.00187 |
| Haiku 4.5 | $0.00017 | $0.00093 |
Grade A, and why
merit-documents 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 2mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merit document sync
Every transaction needs its original receipt/invoice for accounting. This skill finds the ones that don't have it, tries to locate the file, and flags the rest.
Full design + config: docs/document-sync.md.
Audit (read-only)
List invoices with no attached document. Purchases by default (an expense with no
receipt is the real gap); --sales also checks issued invoices.
elnora-merit documents list-missing --from 2026-01-01 --to 2026-07-31
elnora-merit documents list-missing --sales
Output: { count, missing: [{ kind, id, billNo, partyName, docDate, grossTotal, currency, paid }] }.
The signal is Merit's own FileExists flag on each invoice header.
Find + resolve
elnora-merit documents run # audit → search → match → digest (READ-ONLY)
elnora-merit documents run --apply # also stage matched PDFs for a UI upload
elnora-merit documents run --apply --rebook # attach in place (delete+recreate; unpaid)
elnora-merit documents run --apply --rebook --force # also paid (drops payment link — re-book it)
Matching scores each candidate PDF on amount (0.5) + date (0.3) + party name (0.2); ≥0.9 auto-resolves, 0.6–0.9 is reported to confirm by hand.
Attach limit: Merit's API only accepts a file at invoice creation time — there is
no attach-to-existing endpoint. So run --apply defaults to staging (copy the PDF to
a folder, named by invoice, for a 2-second drag into the Merit UI). --rebook
delete+recreates instead; avoid it on paid invoices unless you will re-book the payment.
Best practice: attach the receipt in the same purchase-invoices create call for new bills.
Sources (local + Gmail/Drive/anything)
Configure in ~/.config/elnora-merit/docsync.json (see docsync.example.json):
{ "type": "dir", "path": "~/Downloads" }— scan a local folder for PDFs and image receipts (.jpg/.png/.heic/.webp/…).{ "type": "command", "command": "…" }— run your own fetcher for Gmail/Drive/scanner; it writes files locally and prints one JSON line per candidate ({"path":"…","amounts":[…],"dates":[…],"text":"…"}). No provider SDK or secret lives in this package.
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.
- 2mo ago First seen · 79 lines · 172 tokens per session scan A 3d9cfd402b86
merit-documents is a skill published in the GitHub repository Elnora-AI/elnora-merit-aktiva (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 172 tokens to every session and 933 once invoked, about $0.0007 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 2026-08-31.
merit-documents compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| merit-documentsElnora-AI/elnora-merit-aktiva | Skill | 10 | 5d ago | Apache-2.0 | A | 172 | Claude Code |
| officecli-financial-modeliOfficeAI/OfficeCLI | Skill | 33k | 8d ago | Apache-2.0 | A | 222 | Claude Code, Codex |
| recipe-create-expense-trackergoogleworkspace/cli | Skill | 32k | 4d ago | Apache-2.0 | A | 22 | Claude Code, Codex |
| investor-materialsericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 87 | Claude Code, Codex |
| Invoice OrganizerCraftOS-dev/CraftBot | Skill | 402 | 2d ago | MIT | A | 13 | Claude Code, Codex |
| capitoltrades-cliItamarZand88/CLI-Anything-WEB | Skill | 240 | 6d ago | MIT | A | 111 | Claude Code |
| reading-deduction-certkazukinagata/shinkoku | Skill | 367 | 1mo ago | MIT | A | 63 | Claude Code |