Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-boxnpx agentmods add skills/stevengonsalvez/agents-in-a-box/needsWrote 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/stevengonsalvez/agents-in-a-box/needs)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/needs"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/needs/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/stevengonsalvez/agents-in-a-box/needs"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/needs.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 | $0.00095 | $0.03089 |
| Opus 5 | $0.00048 | $0.01545 |
| Sonnet 5 | $0.00019 | $0.00618 |
| Haiku 4.5 | $0.00010 | $0.00309 |
Grade B, and why
ainb-fleet:needs scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
> [`ainb fleet atc setup`](../atc/SKILL.md) (into `~/.claude/settings.json`). How it starts
The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ainb fleet:needs — center control panel
Single place to see every claude session that wants your attention. Four signal kinds classified per session, priority ASK > ERR > IDLE > WAIT.
needs vs fleet-needs — which skill?
This skill (
needs) is the plain, always-available control panel. It is prompt-driven: render the HUD, fire AskUserQuestion, route answers back. It needs no workflow gate and works everywhere.
/ainb-fleet:fleet-needsis the workflow-backed "Jarvis" cockpit — same purpose, but it runs the deterministichangarworkflow (verb=needs) for discover→enrich→prioritize, batches enrichment in a single agent, and adds key-route ASK answering (presses the target's picker keys via tmux for an open AskUserQuestion). It requiresCLAUDE_CODE_WORKFLOWS=1; with the gate off it falls back to this skill.Rule of thumb: reach for
fleet-needswhen the workflow gate is on and you want the batched/cockpit path; otherwise useneeds. Both read the same underlyingainb fleet needsdata, so the panel content is identical.
Source of truth — materialized current_state (hooks), tmux fallback
ainb fleet needs reads the event-sourced read model first. Claude Code
hooks append lifecycle events to events.jsonl; notifyd ingests them into a
SQLite current_state table that materializes the latest stage per session
(ASK / ERR / WAIT / IDLE / RUNNING / DONE). For each session (keyed by cwd —
the fleet's cross-source dedupe key), the reader resolves one of three ways:
| resolution | when | what happens | row source |
|---|---|---|---|
| hook-authoritative | a materialized ASK/ERR/WAIT/IDLE row exists for the cwd (source = hook) |
use it directly — no pane scan | "hook" |
| hook-healthy | the hook says RUNNING / DONE | not a "need" — emit nothing, skip the pane scan | — |
| fallback | no usable hook row — absent from current_state (a non-Claude session like Codex/Gemini fires no Claude hooks), source = tmux, or a stale row |
run the live classify() pane/transcript scan, exactly as before the event store existed |
"tmux" |
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 · 280 lines · 95 tokens per session scan B 8d461dc5e8a5
ainb-fleet:needs is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 3,089 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
chinese-git-workflow
A Git workflow guide tailored to Chinese-hosted platforms such as Gitee, Coding.net, and GitLab, including their code-review and build systems.
chinese-commit-conventions
A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.
using-superpowers
A set of rules for finding and using assistant skills at the start of every conversation. It says to check for relevant skills before responding, including when asking a clarification question.
platform-api
Queries the Genesys Cloud Platform API schema for endpoint details, permissions, parameters, and response formats. Use when user asks about Genesys Cloud API endpoints (e.g., "/api/v2/assistants/queues"), API documentation, API permissions, schemas, capabilities, or when implementing Genesys Cloud operations.
chinese-code-review
Chinese-language guidance for giving professional, tactful code-review feedback while still calling out real problems.
mcp-builder
A guide to building MCP servers, which let AI assistants call tools or read connected data. It covers server structure, tool design, validation, testing and deployment in TypeScript and Python.