5338e422f9
docs: sync README with updated belt SKILL.md
...
local file upload, --json for all list commands, belt balance,
multi-function apps, plugin init for all agents, .beltsh/config.json
disable, trust/security links
2026-07-13 15:44:47 +02:00
457a7a97ac
update: sync SKILL.md with latest from skills repo
2026-07-13 15:33:08 +02:00
896f39250a
security: harden SKILL.md for trust hub / snyk / socket audits
...
- install: package managers first, curl-to-file with review step second
- skills: add realtime security scanning language, github.com paths included
- knowledge/suggest: add prompt injection trust boundary guardrails
- allowed-tools: pin brew/scoop to exact packages, no wildcards
- frame CLI as constrained interface (safer than raw API calls)
2026-07-12 17:58:49 +02:00
98b69d3d4b
fix: replace curl|sh install with download-then-run
...
stops security auditors (gen agent trust hub) and Claude Code from
flagging the install as remote code execution. same fix as belt-sh/skills.
2026-06-30 01:11:06 +02:00
ddf5dc09ec
replace fal app references with openai, reve, and pruna
...
stop advertising fal as the default image provider. diversify
examples across openai/gpt-image-2, reve/create, pruna/p-image,
and pruna/p-image-upscale.
2026-06-22 02:09:49 +02:00
f7d0e3ab65
document --local flag for project-level skill installs
2026-05-10 11:34:26 +02:00
96d0f25b35
promote skill use over add, document github url support
2026-05-10 11:12:48 +02:00
f5c7480bed
document skill install behavior — auto-detection, --agent, --dir flags
2026-05-10 11:06:48 +02:00
08b1b07dd5
add bundled belt skill (.agents/skills + .claude symlink)
2026-05-10 10:41:19 +02:00
3cab4e6d9d
symlink CLAUDE.md → AGENTS.md
2026-05-10 10:38:21 +02:00
7fc61fd2c2
initial belt cli public repo
...
docs, install scripts, agent context (CLAUDE.md, AGENTS.md),
examples, and issue templates. source is closed — this repo
serves as the public resource hub for belt cli usage.
2026-05-10 10:29:12 +02:00
okaris