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 skills/to-agent/agent-exec/aclnpx skills add to-agent/agent-exec --skill aclgit clone --depth 1 https://github.com/to-agent/agent-execWhat 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 | $0.00000 | $0.00351 |
| Opus 5 | $0.00000 | $0.00176 |
| Sonnet 5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
Grade C, and why
acl scanned grade C with 2 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 yesterday.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- A plain string deny pattern such as `"rm -rf /"` only blocks that exact command and argument form. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -H "X-API-Key: <API_KEY>" http://<host>/api/acl What it actually says
SKILL: acl
Endpoint: GET /api/acl
Description: Get the access control list — allowed and denied commands
Overview
Returns the current ACL configuration: which commands are allowed and which are denied.
curl -H "X-API-Key: <API_KEY>" http://<host>/api/acl
Response
{"allow": ["aexec --version", "date", "echo agent exec ok"], "deny": ["/^sudo/", "/rm\\s+-rf/"]}
ACL Pattern Types
| Pattern | Example | Match behavior |
|---|---|---|
| String | "aexec --version" |
Exact match for this command and argument |
| Glob | "hermes *" |
Explicit wildcard match; allows any arguments to hermes |
| Regexp | "/^sudo/" |
Regex match against the submitted command and arguments |
deny is evaluated before allow. A command matching any deny pattern is rejected even if it matches an allow pattern.
A rule like cmd * allows any arguments to cmd; treat broad glob rules as host policy, not agent permission to assume safety.
Notes
- ACL rules are evaluated server-side against the submitted command and arguments
- Plain string patterns are exact matches only
- A plain string deny pattern such as
"rm -rf /"only blocks that exact command and argument form. - Use explicit glob or regexp deny patterns to cover argument variants, for example
"/\\brm\\b.*(-rf|-fr|--recursive|--force)/".
Authentication
Required: X-API-Key: <API_KEY>.
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.
- yesterday First seen · 40 lines · 0 tokens per session scan C 197ab14cab51
acl is a skill published in the GitHub repository to-agent/agent-exec (1 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 351 tokens. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
add-provider
Add or extend an open-source OOMOL Connect provider under src/providers, including provider definition, action schemas, local executors, credential validation, examples, and generated catalog updates.
vs-product-qa
Answer Viking AI Search product questions, CLI usage questions, API/auth questions, configuration questions, and troubleshooting questions by grounding every claim in either the installed vs CLI's own output or official Volcengine documentation. Never fabricate.
vs-search
Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.
vs-shared
Shared SearchCLI setup: install, authenticate, run doctor, and verify the local environment.
local-search
Skill "local-search" from taxueseek/argo, covering local search 子技能, 设计原则, 本地引擎列表（33 个，29 个默认启用）, 调用方式 and 直接调用子技能（单引擎）.
scrape-structured-data
Get the repeating records off a web page (product grids, search results, job listings, news feeds, tables) as JSON, without writing CSS selectors and without spending a model call to read the HTML. Works on sites with no API, including ones behind a login or bot protection. Runs locally, one binary, no API key. Use…