Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Requests

ASecurity

> **Doc class**: Request ticket (date-prefixed non-lifecycle — per `@rules/docs-numbering.md`). Per-task work breakdown unit for progress tracking. **Not** a feature-level requirements doc — for that see `../1-requirements.md`. > **Created**: 2026-10-04 > **Status**: Completed > **Priority**: P2 > **Tech Spec**: [2-tech-spec.md](../2-tech-spec.md) — § 3.5, § 5 task 9 > **Requirements**: [1-requirements.md](../1-requirements.md) — FR-26, NFR-7 > **Code location**: this repository — `skills/age...

192 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsnodetestinggit

Works with

claude codecli

Security Analysis

A100/100

Pro scans all 12 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add sd0xdev/sd0x-harness --skill requests --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Requests?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Requests
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sd0xdev-requests-10e3a5d6/badge)](https://www.skillsdirectory.com/skills/sd0xdev-requests-10e3a5d6)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
2026-10-03-t1-scaffold-reducer-sanitize.md
# T9 — `/agentctl-setup`: opt-in install and first task for plugin users

> **Doc class**: Request ticket (date-prefixed non-lifecycle — per `@rules/docs-numbering.md`). Per-task work breakdown unit for progress tracking. **Not** a feature-level requirements doc — for that see `../1-requirements.md`.
> **Created**: 2026-10-04
> **Status**: Completed
> **Priority**: P2
> **Tech Spec**: [2-tech-spec.md](../2-tech-spec.md) — § 3.5, § 5 task 9
> **Requirements**: [1-requirements.md](../1-requirements.md) — FR-26, NFR-7
> **Code location**: this repository — `skills/agentctl-setup/`, `mods/agentctl/`, `.claude-plugin/marketplace.json`

## Background

The mod moved into this repository under `mods/agentctl/` (user decision, 2026-10-04) and the plugin
never installs it. Using it meant `--plugin-dir` and a hand-written task JSON. Plugin users need one
friendly path: understand what it does, check the host, install after approval, and get a first task
line they can send.

## Requirements

- An `agentctl` entry in the marketplace (relative source `./mods/agentctl`) so the mod installs as a separate, optional plugin
- `/agentctl-setup`: explain → check → install → first task → optional deny rules; `--task`, `--status`, `--uninstall`
- A helper with `doctor`, `task-line` and `deny-rules`, each printing one JSON document
- Every install, enable, settings write and uninstall is asked first; the task line is the user's to send

## Scope

| Scope | Description |
| ----- | ----------- |
| In | Tech spec § 3.5 and § 5 task 9 |
| Out | Changes to the mod's behaviour beyond declaring its module format; CI for the mod's own tests |

## Related Files

| File | Action | Description |
| ---- | ------ | ----------- |
| `skills/agentctl-setup/SKILL.md` | New | The setup workflow |
| `skills/agentctl-setup/scripts/agentctl-setup.js` | New | `doctor`, `task-line`, `deny-rules` |
| `test/skills/agentctl-setup.test.js` | New | Skill and helper tests |
| `.claude-plugin/marketplace.json` | Modify | `agentctl` entry |
| `mods/agentctl/package.json` | New | ES-module declaration |
| `docs/skill-catalog.yml`, `README*.md` | Modify | Catalog entry and counts |

## Acceptance Criteria

- [x] `doctor` reports the Claude Code version against 2.1.288, `git`, the mod manifest, `disableAllHooks` in user or project settings, and install state as not installed, unreadable or `{ id, enabled }`
- [x] The marketplace lists `agentctl` from `./mods/agentctl`; a real install from it loads the mod in a new session, and uninstalling leaves the settings and plugin records byte-identical once the host's own leftovers are removed
- [x] An installed but disabled mod is reported and enabled only after approval, before any task is built
- [x] `task-line` prints only a line the mod accepts: it runs the mod's `validateTask`, refuses checks the mod's `classify` would not pass and needs-user commands that would not ask, and loads without Node's syntax detection
- [x] The skill never sends `/agentctl task set` itself and tells the user why the line is theirs to send
- [x] `deny-rules` keeps every other setting, is idempotent, leaves invalid or oddly shaped files untouched, and never offers `git push`
- [x] `--uninstall` asks first and names the mod's data file
- [x] The skill is in the catalog and every README count and catalog block; the global skill, catalog and manifest tests pass
- [x] Pass /codex-review-fast
- [x] Pass /precommit
- [x] Pass /codex-review-doc

## Progress

| Phase | Status | Note |
| ----- | ------ | ---- |
| Analysis | Done | Tech spec § 3.5; marketplace relative sources and the plugin CLI checked against the docs and `claude plugin --help` (2.1.289) |
| Development | Done | Skill, helper, marketplace entry, catalog and six READMEs; review fixes: ES-module declaration, classifier check of each command, disabled-install branch, settings files that are not a JSON object left untouched, free-text answers passed through an allocated file instead of a command line, mode dispatch before step 1 |
| Testing | Done | `test/skills/agentctl-setup.test.js` 28 pass (AC3, AC4 and AC7 evidence tests included); `npm test` 5111 pass, 0 fail, covering the global skill, catalog and manifest tests; mod `claude plugin test .` 145 pass |
| Acceptance | Done | 2026-10-04 live: local marketplace add → `claude plugin install agentctl@sd0xdev-marketplace` → `/agentctl` answered in a new `claude -p` session → `doctor` read `{ id, enabled: true }` → uninstall and marketplace remove; the host left an empty `extraKnownMarketplaces`, a plugin cache and `installed_plugins.json`, which were removed, and `~/.claude/settings.json` and the plugin records were byte-identical to the backup. `/codex-review-fast` (thorough, four rounds): ✅ Ready. `/precommit`: ✅ PASS. `/codex-review-doc` over the skill, tech spec, this ticket, the mod README and the six READMEs (three batches): ✅ Mergeable. `/create-request --update --verify-ac` (2026-10-04): every AC Complete at High, accounted one result per AC |

## References

- Tech Spec: [2-tech-spec.md](../2-tech-spec.md)
- Intent: [intent-agent-control-plane-mod.md](../intent-agent-control-plane-mod.md)

Attribution

sd0xdevsd0xdev
View sourceSee grades on GitHubMore from sd0xdev →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →