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/masaomi/kairoschain_2026/pluginnpx skills add masaomi/KairosChain_2026 --skill plugingit clone --depth 1 https://github.com/masaomi/KairosChain_2026Wrote 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/masaomi/kairoschain_2026/plugin)<a href="https://agentmods.dev/skills/masaomi/kairoschain_2026/plugin"><img src="https://agentmods.dev/badge/skills/masaomi/kairoschain_2026/plugin.svg" alt="Measured on agentmods" 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 | $0.00089 | $0.01098 |
| Opus 5 | $0.00044 | $0.00549 |
| Sonnet 5 | $0.00018 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
account_manager 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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
account_manager
A ledger for one person with two purses: a sole proprietorship whose owner also buys groceries. The books separate for tax; the money does not. It knows no country's rules — the chart of accounts, the tax labels, the fiscal year and the import profiles are all configuration.
The one thing to understand first
a receipt, a CSV row, a sentence
│
▼
PROPOSAL ──── visible to queries
│ counted by NO report
│ carries who authored it
│
the operator posts it ◀── the only way across
│
▼
POSTING ──── balanced, both books balance alone
│ counted by every report
▼
P&L · balance sheet · reconciliation
Nothing crosses that line without an explicit operator call. An agent that misreads a receipt costs a correction, never a wrong figure.
The six tools
| Tool | Use it for |
|---|---|
am_entry |
post; edit or note a posting whose month is open; correct a sealed year; record, post, discard or un-discard a proposal; confirm a join |
am_import |
CSV rows → proposals, keyed by (profile, reference) |
am_query |
find postings, proposals, or the state of each month |
am_report |
profit and loss, balance sheet, reconciliation — markdown, CSV or figures |
am_receipt |
copy evidence in under its content hash, bind it, list what has none |
am_close |
close a month, re-open one, take the annual close |
The rules that will surprise you
Two dates, one job each. The transaction date is when it happened, and it alone decides which month the entry belongs to. The settlement date is when money moved, and it is used by reconciliation and by nothing else. A posting where no money moved — an owner draw, a correction — carries no settlement date, and putting one on it is refused.
Each book balances alone. Pay a business expense with a private card and the ledger completes the entry through the configured owner-draw pair, so the business book and the private book each balance on their own. You give it two lines; it stores four, and says so.
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.
- 5d ago First seen · 97 lines · 89 tokens per session scan A 5d9223c6a182
account_manager is a skill published in the GitHub repository masaomi/KairosChain_2026 (7 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 1,098 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
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
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
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
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.