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 flumpiey/manager-mcp --skill manager-accountinggit clone --depth 1 https://github.com/flumpiey/manager-mcpWrote 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/flumpiey/manager-mcp/manager-accounting)<a href="https://agentmods.dev/skills/flumpiey/manager-mcp/manager-accounting"><img src="https://agentmods.dev/badge/skills/flumpiey/manager-mcp/manager-accounting/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/flumpiey/manager-mcp/manager-accounting"><img src="https://agentmods.dev/badge/skills/flumpiey/manager-mcp/manager-accounting.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 | $0.00073 | $0.01282 |
| Opus 5 | $0.00036 | $0.00641 |
| Sonnet 5 | $0.00015 | $0.00256 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
manager-accounting 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manager.io accounting
Pairs with the manager-mcp MCP server.
Discovery first
- Call
list_resources. - Trust its
read_only,write_scopes,delete_scopes,effective_write_scopes, andboundary. - Use only collections named in that response for
list_records/get_record.
Boundary
- Empty scopes → read-only tool set (10 tools).
- Mutations need
MANAGER_MCP_WRITE_SCOPES(create/update) and/orMANAGER_MCP_DELETE_SCOPES(delete). Delete is never implied by write. - Recommended write scopes:
banking,sales,parties(not all nine domains). - Never attempt access-token, chart-of-accounts / control-account forms, tax/currency minting, starting balances, or other denylisted paths.
rawin WRITE_SCOPES restores the full CRUD set (advanced escape hatch).
Config
MANAGER_API_URL- opaque base URL (include/api2when required)MANAGER_API_KEY-X-API-KEY; never echo- Scope CSVs must match between local
.envand the MCP hostenvblock - If a tool says Manager is not reachable: tell the user to open Manager (API enabled) and retry. Do not treat it as an MCP server crash.
Precondition responses
When a tool returns status: precondition_failed:
- Relay each item's
how_to_createtext to the user verbatim. - Stop. Do not invent a workaround or skip setup steps.
Task tools (prefer over CRUD)
Registered when required scopes are in effective_write_scopes:
| Tool | Scopes | Bookkeeper sentence |
|---|---|---|
issue_sales_invoice |
sales | Issue a sales invoice |
issue_purchase_invoice |
purchases | Issue a purchase invoice |
issue_quote |
quotes | Issue a quote |
convert_quote_to_invoice |
quotes + sales | Turn this quote into an invoice |
record_customer_payment |
banking | Record a customer payment against an invoice |
record_supplier_payment |
banking | Pay a supplier invoice |
record_expense |
payroll and/or purchases | Record an expense |
transfer_between_accounts |
banking | Move money between accounts |
post_journal_entry |
ledger | Post a journal entry |
void_document |
matching delete scope | Void this document |
record_customer_deposit |
banking | Record a customer deposit |
issue_deposit_invoice |
quotes | Issue a deposit invoice document |
apply_deposit_to_invoice |
ledger | Apply held deposit to an invoice |
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.
- 9d ago First seen · 117 lines · 73 tokens per session scan A ad9daed90fb2
manager-accounting is a skill published in the GitHub repository flumpiey/manager-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,282 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.