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/execnpx skills add to-agent/agent-exec --skill execgit 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 | $0.00612 |
| Opus 5 | $0.00000 | $0.00306 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
exec scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST http://<host>/api/exec \ How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: exec
Endpoint: POST /api/exec
Description: Execute a command on this machine
Overview
Execute a command via POST /api/exec. The command must be in the exec.allow list and must not match exec.deny.
Request
curl -X POST http://<host>/api/exec \
-H "X-API-Key: <API_KEY>" \
-H "Content-Type: application/json" \
-d '{"args": ["aexec", "--version"]}'
Body
| Field | Type | Description |
|---|---|---|
args |
array | Command and arguments: ["cmd", "arg1", "arg2"] — required |
memo |
string | Optional opaque memo text echoed back by agent-exec; not interpreted or stored |
Body fields other than the listed fields are rejected. cmd, command, env, cwd, and shell return HTTP 400.
Query Parameters
| Parameter | Values | Default | Description |
|---|---|---|---|
format |
json, text |
json |
Response format |
mode |
buffered, stream |
buffered |
Execution mode. stream is direct-command only and is rejected for plugin commands. |
Response
buffered + format=json
{"output": "agent-exec v0.2.0\n", "length": 18, "exitCode": 0, "status": "done", "duration": 3}
stream + format=json
Use streaming only for direct commands. If the command is handled by a plugin, use buffered mode or a plugin-specific /api/command/:name/* route.
NDJSON — one JSON object per line:
{"output":"line1\n","length":6,"status":"running"}
{"output":null,"exitCode":0,"status":"done","duration":42}
ACL
Commands are checked against server-side ACL rules before execution. exec.deny is evaluated before exec.allow.
Plain string patterns are exact matches only. Glob patterns may use *, and regexp patterns use /.../ when the host intentionally wants broader matching.
A rule like cmd * allows any arguments to cmd; treat broad glob rules as host policy, not agent permission to assume safety.
agent-exec executes args as argv. It does not run commands through a shell, and command/args are not accepted from the query string.
Shell metacharacters such as &&, ;, and | are not interpreted by agent-exec itself.
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 · 67 lines · 0 tokens per session scan A 6f0f54b49d92
exec 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 612 tokens. A static security scan graded it A with 1 finding (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…