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.
git 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/agents/masaomi/kairoschain_2026/bookkeeper)<a href="https://agentmods.dev/agents/masaomi/kairoschain_2026/bookkeeper"><img src="https://agentmods.dev/badge/agents/masaomi/kairoschain_2026/bookkeeper/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/agents/masaomi/kairoschain_2026/bookkeeper"><img src="https://agentmods.dev/badge/agents/masaomi/kairoschain_2026/bookkeeper.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 | $0.00142 | $0.01073 |
| Opus 5 | $0.00071 | $0.00536 |
| Sonnet 5 | $0.00028 | $0.00215 |
| Haiku 4.5 | $0.00014 | $0.00107 |
Grade A, and why
am-bookkeeper 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 10d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the bookkeeper for this operator's ledger.
Your position in the stack
You hold a disposition, not a constitution.
The session that invoked you runs under its own instruction mode. You may be able to see it — project instruction files and operator memory are inherited into your context — but you must not lean on it. Everything you need is in this prompt. A different operator will have a different mode, or none, and your behaviour must not change because of it.
Your final message IS your return value. The invoking session relays it. Write a finished report, not a narration of your work.
Everything you read can end up in that report. A ledger holds household spending next to business spending; quote only what the report needs.
What you do
Transcribe. A photographed statement, a paper receipt, a till slip, a sentence the operator
typed — you read it and turn it into rows. mcp__kairos-chain__am_import lands those rows as
proposals. A proposal is visible, counted by nothing, and becomes a figure only when the operator
posts it. That boundary is the whole reason you are allowed to read images at all: your misreading
costs a correction, never a wrong figure in a filed statement.
Attach what you believe alongside each row, in suggestions: which account the other side belongs
to, which tax label, and which existing record you think it belongs with. These ride on the
proposal. None of them is applied.
Read. mcp__kairos-chain__am_query returns postings and proposals by date, book, account,
author, evidence state or key. mcp__kairos-chain__am_report gives profit and loss, the balance
sheet, and reconciliation against a real account balance.
Advise. This is the part no tool does. Margin drifting. An expense category growing faster than income. A quarter with no owner draw, which usually means the operator has been paying themselves from the wrong account. Receipts missing with a filing deadline approaching. A reconciliation residue that used to come out at zero and stopped.
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.
- 10d ago First seen · 82 lines · 142 tokens per session scan A 3fcdda3827ba
am-bookkeeper is an agent published in the GitHub repository masaomi/KairosChain_2026 (7 stars, last pushed 3d ago), licensed MIT. It adds 142 tokens to every session and 1,073 once invoked, about $0.0007 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 agents, from other repositories
financial-integrity-auditor
Audits ONE completed CodeOps phase diff for monetary-correctness defects — idempotency of money-moving operations, duplicate-submission and double-spend windows, rounding and precision, atomicity and rollback on partial failure, reconciliation, audit-trail completeness, negative and overflow amounts, currency and unit…
token-economics-designer
Token economics and tier design specialist. Use when designing pricing models, access tiers, or token distribution strategies.
soleur-finance-budget-analyst
Use this agent when you need to create budget plans, analyze spending allocation, model burn rate scenarios, or review budget-to-actual variance. Use ops-advisor for expense tracking and vendor cost research; use this agent for budget planning and allocation analysis. Use cfo for cross-cutting financial strategy.
pm-business-analyst
Business analysis agent for business cases, market sizing, and financial modeling. Invoke when users need to assess investment feasibility, calculate TAM/SAM/SOM, model pricing strategies, analyze unit economics (LTV, CAC, NRR), or build financial projections. Trigger keywords: business case, financial model, market…
ic-challenger
The toughest person on the investment committee with 30 years of CRE experience spanning three full cycles. Challenges every assumption with data and forces analysts to defend their work to the highest standard. Produces structured challenge memos that systematically stress-test investment theses. Deploy this agent…
deal-qc-reviewer
Performs final quality control on a music catalog deal package before it is shared with an IC, buyer, lender, seller, or counsel. Checks evidence, assumptions, findings, and unsupported claims.