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-palk-workspacegit 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-palk-workspace)<a href="https://agentmods.dev/skills/elnora-ai/elnora-merit-aktiva/merit-palk-workspace"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-palk-workspace/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-palk-workspace"><img src="https://agentmods.dev/badge/skills/elnora-ai/elnora-merit-aktiva/merit-palk-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00208 | $0.01592 |
| Opus 5 | $0.00104 | $0.00796 |
| Sonnet 5 | $0.00042 | $0.00318 |
| Haiku 4.5 | $0.00021 | $0.00159 |
Grade B, and why
merit-palk-workspace 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 12d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
`--data '<json>'` or `--file <path>`. Run any command's `--help` for its field summary. How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merit Palk Workspace (payroll)
Router for Merit Palk (payroll) work via the elnora-merit palk … CLI. Palk is a
distinct Merit product from Aktiva accounting: different host (palk.merit.ee), its own
API credentials, and a v1-only API. Load the topic skill for the procedure first — it
carries the correct payroll method and the exact payload schema — then run the CLI.
Dispatch table
| Intent | Skill |
|---|---|
| Onboard a new employee (+ first contract + first base salary), add contacts, update a base salary agreement | merit-palk-employees |
| Run payroll: enter salaries & withholdings, record absences / leave / sick days | merit-palk-payroll |
| Read the employee list, base-salary agreements, salary & hours report, GL batch (to post into accounting), vacation obligation balance | merit-palk-reports |
| Per-employee setup: basic exemption (tax-free) usage, vacation liability rate, reduced work capacity; create dimensions (department / cost centre / project) | merit-palk-settings |
| One-off CLI call | elnora-merit palk <group> <verb> directly |
Company-specific data
These skills are generic — the correct Merit Palk method, with no company account codes,
employee data, or import IDs baked in. Real salary/withholding import IDs, GL account codes,
department/cost-centre/project codes, and employee identifiers belong in a company books
reference kept in your references dir (MERIT_REFERENCES_DIR, default ~/.config/elnora-merit),
not in this public repo. When one is available, load it alongside the topic skill before
building a payload so the right codes are used.
Note: elnora-merit profile sync snapshots Aktiva reference data only (accounts, banks,
VAT, financial years) into company-profile.json. Palk import IDs are not included — keep
those in your prose books reference.
The rules that govern ALL Palk writes
- There is no delete or update via the API. Every correction is made manually in the Merit Palk UI. A wrong POST cannot be rolled back through the API — so confirm each payload with the user before sending, and prefer a test company first.
- One record per call. Each
send*endpoint posts a single flat JSON object (e.g. one salary row, one absence). To enter many, loop — there is no batch array and no transaction, so a partial run leaves partial data that can only be fixed in the UI. - Import codes must already exist in Merit Palk and be numeric.
Typecode/SalaryTypeImpCode(and a customContractId) are numbers (≤13 digits, no letters/symbols) that you first set on the matching card in Merit Palk (Payroll → Salary types → "Import ID", etc.).ContractCode/ContractIdalso accept the employee's Personal ID code — the simplest key when you haven't assigned custom contract codes. Typecodesign picks the table: positive = a Salary type import ID; negative = a Withholding type import ID. AbsenceTypecodes are a fixed Merit-provided enum (you do not create them) — seemerit-palk-payroll.
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.
- 12d ago First seen · 100 lines · 208 tokens per session scan B e748bb9e5662
merit-palk-workspace is a skill published in the GitHub repository Elnora-AI/elnora-merit-aktiva (8 stars, last pushed 5d ago), licensed Apache-2.0. It adds 208 tokens to every session and 1,592 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
capitoltrades-cli
Queries US congressional stock trades (STOCK Act disclosures) on capitoltrades.com via the cli-web-capitoltrades command-line tool — trades with rich filters, politician profiles and leaderboards, issuer lookup with price history, plus insight articles, buzz, and press. Use when the user asks about congress trades…
watch
Watch live IDX turnover and order books for unusual activity — value surges, auto-reject approach, one-sided depth, walls appearing or withdrawn, quiet stocks waking up, UMA flags — plus delayed print-by-print attribution and end-of-day broker context. Use when the user runs /watch, or asks what is trading right now…
stockbit-status
Check whether the Stockbit session is still valid — main session expiry, whether trading credentials are stored, and the current trading mode. Use when the user asks "am I still logged in to Stockbit", "has my session expired", "is trading on", or when a stockbit MCP tool starts failing with an auth error.
stockbit-auth
Log in to Stockbit and capture the session for this server — opens the browser login flow and verifies the token was stored. Use when the user asks to log in or re-authenticate to Stockbit, or after a status check reports the session expired, HTTP 401, or logged out.
trade-with-guardrails
Place an order through the user's own Stockbit account safely — check the mode, size the position from a risk budget, preview, read the summary back to the human, and only then write. Use when the user asks to buy, sell, amend or cancel an order, or to size a trade.
bandar-check
Answer "who is accumulating this stock?" for an IDX ticker using Stockbit broker-flow data. Use when the user asks about bandar, big money, accumulation, distribution, foreign flow, asing, or who is on the other side of the tape.