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 instructions/teamtinvio/jaz-ai/agents-mdgit clone --depth 1 https://github.com/teamtinvio/jaz-aiWrote 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/instructions/teamtinvio/jaz-ai/agents-md)<a href="https://agentmods.dev/instructions/teamtinvio/jaz-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/teamtinvio/jaz-ai/agents-md.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 5.1 | $0.00632 | $0.00632 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
jaz-ai AGENTS.md 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jaz AI · Agent Skills
Agent skills for the Jaz accounting platform. Works with Claude Code, Google Antigravity, OpenAI Codex, GitHub Copilot, Cursor, and any tool that supports the Agent Skills open standard.
Also fully compatible with Juan Accounting.
Skills
| Skill | What it teaches an agent |
|---|---|
| jaz-api | 141 production rules, every endpoint, error catalog, field mapping. Agents write correct Jaz API code on the first call. |
| jaz-cli | The clio command surface, auth precedence, output formats, pagination |
| jaz-conversion | Xero, QuickBooks, Sage, MYOB, Excel migration: CoA mapping, FX, clearing accounts, trial balance verification |
| jaz-jobs | 12 close playbooks (month / quarter / year-end, bank-recon, GST/VAT, payment-run, credit-control, supplier-recon, audit-prep, FA-review, statutory-filing) + Singapore Form C-S |
| jaz-recipes | 13 IFRS recipes (loans, IFRS 16 leases, depreciation, FX reval, ECL, IAS 37 provisions, asset disposal) + 13 calculators |
| jaz-pseudo-sql | Read-only pseudo-SQL over the curated reporting schema for ad-hoc questions |
| jaz-kit | Multi-organization operator workspace: per-org context, resumable closes, review queue |
Install
# Auto-detect your AI tool and install all 7 skills
npx jaz-clio init
# Or one skill at a time
npx jaz-clio init --skill jaz-api
npx jaz-clio init --skill jaz-conversion
For Claude Code, prefer the marketplace plugin (skills + MCP server in one install):
/plugin marketplace add teamtinvio/jaz-ai
Skill paths
Skills are available at both standard discovery paths in this repo:
.agents/skills/· Agent Skills open standard (Codex, Copilot, Cursor, Antigravity, Windsurf, Goose, Roo Code, Junie, Amp).claude/skills/· Claude Code native path
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 · 50 lines · 632 tokens per session scan A 36022e1f44cd
jaz-ai AGENTS.md is an instructions file published in the GitHub repository teamtinvio/jaz-ai (7 stars, last pushed yesterday), licensed MIT. It adds 632 tokens to every session, about $0.0032 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 instructions, from other repositories
sonicjs AGENTS.md
AGENTS.md instructions for SonicJs-Org/sonicjs, covering sonicjs agent guidelines, decision tree — code exploration, rtk (rust token killer), caveman mode and delegation — cavecrew subagents.
gorest AGENTS.md
AGENTS.md instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
gorest CLAUDE.md
Claude Code instructions for pilinux/gorest, covering claude.md, authoritative references, files to never read or modify, common commands and architecture (the big picture).
symfony-flex-backend CLAUDE.md
Claude Code instructions for tarlepp/symfony-flex-backend, covering what is this?, table of contents ᐞ, ai documentation map ᐞ, version sources of truth ᐞ and project architecture ᐞ.
symfony-flex-backend copilot-instructions.md
Copilot instructions for tarlepp/symfony-flex-backend, covering what is this?, table of contents ᐞ, purpose ᐞ, architecture rules ᐞ and php and symfony rules ᐞ.
sonicjs CLAUDE.md
Claude Code instructions for SonicJs-Org/sonicjs, covering sonicjs ai development guidelines, core technology stack, workspace boundary (conductor), architecture direction: document model (authoritative) and the 5 document tables (migration 0002documents.sql).