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 skills add kajogo777/bento --skill cligit clone --depth 1 https://github.com/kajogo777/bentoWrote 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/kajogo777/bento/cli)<a href="https://agentmods.dev/skills/kajogo777/bento/cli"><img src="https://agentmods.dev/badge/skills/kajogo777/bento/cli/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/kajogo777/bento/cli"><img src="https://agentmods.dev/badge/skills/kajogo777/bento/cli.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 | $0.00000 | $0.00858 |
| Opus 5.5 | $0.00000 | $0.00343 |
| Sonnet 5.5 | $0.00000 | $0.00172 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
cli 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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bento CLI Skill
Bento packages AI agent workspace state into portable, layered OCI artifacts — everything git doesn't track: agent memory, dependencies, build caches, conversation history, session state. Checkpoints are standard OCI images pushable to any container registry.
Commands
bento init # initialize workspace tracking
bento save -m "message" # save a checkpoint
bento open <ref> # restore checkpoint (ref: cp-1, latest, tag, digest)
bento open undo # undo last open
bento list # list checkpoints
bento status # show head, changes, remote sync
bento diff # workspace vs latest
bento diff cp-2 cp-5 # between two checkpoints
bento tag <ref> <name> # tag a checkpoint
bento inspect [ref] # metadata and layers (--files for file list)
bento push [remote] # push to OCI registry
bento pull # pull from remote
bento gc # garbage collection
bento env set|unset|show|export # manage env vars and secret refs
bento watch # auto-checkpoint on file changes
bento add <file> --layer <name> # add file to a layer
bento keys generate|list|public # manage Curve25519 keypairs
bento secrets export # export encrypted secret envelope
bento sessions [inspect] # list/inspect agent sessions
bento explore # interactive checkpoint browser
Global flags: --dir <path> (workspace directory), -v (verbose), --help
Key Concepts
Checkpoints — Snapshots stored as OCI images. Auto-numbered (cp-1, cp-2), content-addressed by digest, taggable. latest always points to most recent.
Layers — Files split into deps (node_modules, .venv — large, rarely changes), agent (memory, config — small, changes often), project (catch-all). Identical layers are deduplicated across saves.
What ships with it
28 files 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.
- add.go 3.5 KB
- diff.go 21 KB
- env_test.go 14 KB
- env.go 11 KB
- explore.go 1.3 KB
- gc.go 1.8 KB
- init.go 2.1 KB
- inspect.go 12 KB
- keys.go 3.7 KB
- list.go 1.8 KB
- lock.go 829 B
- open_test.go 2.1 KB
- open.go 20 KB
- pack_progress_test.go 2.6 KB
- pack_progress.go 3.6 KB
- pull.go 3.0 KB
- push.go 10 KB
- recipients.go 3.5 KB
- root.go 6.8 KB
- save_core.go 29 KB
- save.go 1.7 KB
- secrets_layer.go 1.4 KB
- secrets.go 5.0 KB
- sessions.go 8.2 KB
- skill.go 387 B
- status.go 9.0 KB
- tag.go 883 B
- watch.go 7.6 KB
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.
- 1mo ago First seen · 80 lines · 0 tokens per session scan A 6a77afd152c8
cli is a skill published in the GitHub repository kajogo777/bento (22 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 858 tokens. 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 2026-08-30.
Other skills, from other repositories
ecspresso
ECS deployment tool - deploy, manage, and troubleshoot ECS services.
container-manager-podman-operations
Rootless Podman pod/kube operations via the container-manager-mcp MCP server — pods (create/list/stats/top/inspect/logs/stop/rm), Kubernetes YAML interop (generate/play kube), checkpoint/restore, pod-scoped networks and volumes, health checks, and system prune. Use when the agent must drive Podman pod-level workloads…
agent-context-crystallizer
Preserve high-signal work context with local checkpoints and session crystals using the agent-crystallize CLI. Use before compaction, handoff, session end, cross-agent transfer, after major decisions/findings/failures, or when the user asks to checkpoint, crystallize, preserve context, save open loops, or create a…
cdf-orchestration-setup
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection…
doca-argus
Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the BlueField and attached host for suspicious activity, integrity violations, and operational anomalies, and forwards findings to a SIEM (Splunk / ELK / Sentinel /…
git-ai-search
Search and restore AI conversation context from git history.