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/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/commands/teamtinvio/jaz-ai/jaz-capabilities)<a href="https://agentmods.dev/commands/teamtinvio/jaz-ai/jaz-capabilities"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-capabilities/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/commands/teamtinvio/jaz-ai/jaz-capabilities"><img src="https://agentmods.dev/badge/commands/teamtinvio/jaz-ai/jaz-capabilities.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 | $0.00009 | $0.00166 |
| Opus 5 | $0.00005 | $0.00083 |
| Sonnet 5 | $0.00002 | $0.00033 |
| Haiku 4.5 | $0.00001 | $0.00017 |
Grade A, and why
jaz-capabilities 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 8d 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.
What it actually says
What Jaz can do
Call the Jaz describe_capabilities tool.
- No argument → the full map: every namespace with its operation count and what it covers.
$ARGUMENTSlooks like a namespace name (e.g.invoices,bank_accounts) → pass it asnamespaceto list that area's operations with their parameters.- Otherwise → pass it as
queryto rank matching operations across all namespaces.
Report the result as a short grouped list, largest areas first, then end with two or three things the user could usefully ask for right now given what they were last working on.
Do not restate any count you did not get from the tool.
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.
- 8d ago First seen · 17 lines · 9 tokens per session scan A 1761bce9da1d
jaz-capabilities is a command published in the GitHub repository teamtinvio/jaz-ai (7 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 166 once invoked, about $0.0000 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 commands, from other repositories
tray-referencia-api
Referência rápida de todos os endpoints da API da Tray, aceita nome do recurso como filtro.
setup-x-api
A guided setup command for the X API, which lets software connect to X, formerly known as Twitter.
setup-x-api.en
Command "setup-x-api.en" from minicoohei/ai-agent-camp, covering x (twitter) api setup, step 0: check setup progress, what you'll do in this session, readiness check and step 1: open x developer portal in browser.
api-resource-ship
TOTAL AUTONOMY — branch + pipeline + commit + push + PR for an API Platform feature. Refuses dirty tree. Loop REQUESTCHANGES cap 3. Skips secrets.
dev
Dev stage — api-platform-implementer reads .claude/last-api-plan.md and implements (writes code, runs phpstan + phpunit + Infection on critical classes).
symfony-api-filters
Build API Platform 4.3 filters with the modern parameters + QueryParameter pattern (never.