run-agent

Run a custom agent by name

Repository: AMindToThink/claude-code-settings
Last source activity: March 7, 2026 at 01:59
Detected SKILL.md language: English
Stars: 4
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/AMindToThink/claude-code-settings --skill run-agent

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name: run-agent
description: Run a custom agent by name
argument-hint: <agent-name> [task description]
disable-model-invocation: true

Delegate the following task to the **$ARGUMENTS[0]** agent. If additional arguments were provided, use them as the task description. If no task description was provided, ask the user what they'd like the agent to do.

View on GitHub

Back to search Back to installation

cited-corpus-audit

Use when fanning out subagents over a corpus (pages, traces, logs, documents) to produce findings that must cite evidence — links, quotes, ids, line numbers. Packages the integrity discipline that keeps agent citations real - freeze the corpus locally, schema-forced per-item results with explicit nulls, verbatim-citation validation against the frozen source, gap-fill for dropped items, journal-based recovery. Triggers - "have agents review each X and report/cite", building datasets from agent analyses, Docent-style trace audits, any workflow where fabricated citations or silently dropped items would corrupt the output.

2026-09-01

handle-machine-shared-memory

Use when a shared multi-user Linux box keeps freezing or going unresponsive from out-of-memory (OOM) events, when one user's process is eating all the RAM, or when someone needs to cap memory so the machine stays usable without starving legitimate work. Covers cgroup-v2 / systemd memory guard rails (MemoryMax / MemoryMin), giving Docker its own capped slice, a preflight that refuses over-budget eval runs, and the reasoning that makes the caps safe. Triggers on "the server keeps freezing", "OOM killed my process / dbus / the session", "someone is hogging all the memory", "put a memory limit on docker/users so the machine never dies", "cgroup memory caps", "MemoryMax", "the box becomes unusable under load". Assumes you have root but NOT hardware control (can't add RAM).

2026-09-01

stackexchange-data

Use when fetching or analyzing StackOverflow / Stack Exchange content (questions, answers, comments, vote scores) for a dataset, audit, or research pipeline. Direct page access is blocked from Matthew's machines (WebFetch refuses the domain; curl gets Cloudflare 403) — this skill gives the working Stack Exchange API path and its empirically-discovered quirks. Triggers - "scrape/fetch/download StackOverflow", "SO answers/comments", "api.stackexchange.com", building datasets from SE sites.

2026-09-01

View all from this repository

run-agent

Source facts

Install options

Review the source files

More from this repository

More from this repository