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 to-agent/agent-exec --skill execgit clone --depth 1 https://github.com/to-agent/agent-execWrote 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/to-agent/agent-exec/exec)<a href="https://agentmods.dev/skills/to-agent/agent-exec/exec"><img src="https://agentmods.dev/badge/skills/to-agent/agent-exec/exec/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/to-agent/agent-exec/exec"><img src="https://agentmods.dev/badge/skills/to-agent/agent-exec/exec.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 | $0.00612 |
| Opus 5.5 | $0.00000 | $0.00245 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago 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 5mo 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
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
A local search component that finds web results using installed command-line tools and page parsers. It supports general web search and extra sources for areas such as Chinese pages, news, code questions, academic work, and reference material.
inkbox-agent-self-signup
Use when guiding or implementing the Inkbox agent self-signup flow, including verification, resend-verification, signup restrictions, and optional signup fields like agent handles or mailbox local parts.
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…
hsi-daily-weight
A market-data lookup for the percentage weights of stocks in Hang Seng family indices. The weight shows how much each constituent stock contributes to an index.