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

Spur

ASecurity

Spur orchestrates AI coding agents (claude/codex/cursor/opencode) via CLI, daemon, web UI, or Telegram. Use when spawning, messaging, automating, or configuring a session, tmux pane, or Spur config. Don't use for driving an agent's CLI, or plain git worktree work.

3 stars
0 votes
0 copies
0 views
Added 10/2/2026
ai-agentsrustgitapi

Works with

cursorcliapi

Security Analysis

A100/100

Scanned 10/2/2026

$npx -y skills add ashugaev/spur --skill spur --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Spur?

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

Security grade badge for Spur
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ashugaev-spur/badge)](https://www.skillsdirectory.com/skills/ashugaev-spur)

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

Download with Pro
Files
SKILL.md
---
name: spur
description: Spur orchestrates AI coding agents (claude/codex/cursor/opencode) via CLI, daemon, web UI, or Telegram. Use when spawning, messaging, automating, or configuring a session, tmux pane, or Spur config. Don't use for driving an agent's CLI, or plain git worktree work.
hostInstall: true
---

SPUR

WHAT SPUR IS

  CLI plus a local HTTP daemon, default `127.0.0.1:4310`, plus a web UI.
  "spawn an agent" means this, not the built-in Agent/Task tool.
  Agents `claude`, `codex`, `cursor`, `opencode` launch full-access, each in a detached tmux pane inside a `git worktree`.
  Global fields in a project `spur.yaml` are silently discarded; put them in `~/.spur/config.yaml`.

INTERFACES

  CLI: `spur --help`, then `spur <command> --help`.
  `$SPUR_SESSION_TOOL_DIR` holds the session-bound wrappers; `ls "$SPUR_SESSION_TOOL_DIR"` enumerates them. Call each as `"$SPUR_SESSION_TOOL_DIR/<tool>"`, never bare.
  Session variables: `env | grep '^SPUR_'`.
  Automatic reminder limits: `docs/configuration.md#automatic-reminders`.
  Spur ToDo: ledger starts empty, no code path seeds an item; the agent adds one item per step, before the step, and resolves it after. Empty or open/held work refuses an agent's own completion, self-destruct, and handoff — `todo_ledger_empty`/`todo_open_work` (409); a human `complete`/`handoff` from the CLI or UI is never blocked. Contract: `docs/commands.md#todo`.
  Telegram: agents send with `"$SPUR_SESSION_TOOL_DIR/spur" source reply`; in a private chat a user reply to a bot message reaches the agent that sent it. Contract: `docs/commands.md#source-reply`.
  Stop unwanted auto-pings with `spur auto-ping unsubscribe`. A thread that keeps coming back takes `--thread`; `--event` binds to one emitted occurrence only. Scopes and resume: `docs/commands.md#auto-ping`; API: `docs/daemon-api.md`.

SAFETY

  A daemon on the default port is someone's production instance. Never `daemon start|stop`, kill, or direct-HTTP a daemon you did not start; never repoint `--config` at `~/.spur/config.yaml`.
  Run non-default-instance CLI calls from a neutral cwd — `spawn`/`list` auto-connect the nearest `spur.yaml` upward from cwd and spawn real sessions.
  Never run `gc --execute` against a data dir you do not own; a bare `gc` is the dry run.
  Never run `cache --prune --yes` on a host running agents you do not own; a bare `cache` or `cache --prune` is a dry run.
  Never run `disk-gc --execute` (or `--browser-revisions`) on a host running agents you do not own; a bare `disk-gc` is the dry run.
  `--expose-web` binds `0.0.0.0`, public.
  Agents run full-access — any untrusted prompt from Telegram, GitHub, or Jira runs arbitrary commands as the daemon user.
  Start dev servers with `"$SPUR_SESSION_TOOL_DIR/spur-sidecar" --name <name>`, never a bare dev-server command.
  Read a sidecar's port with `"$SPUR_SESSION_TOOL_DIR/spur-sidecar" ports`, never by grepping `/proc` or session state.

DOCS

  Doc index: https://raw.githubusercontent.com/ashugaev/spur/main/README.md
  Any path under `docs/` resolves as https://raw.githubusercontent.com/ashugaev/spur/main/<path>
  Commands, session tools and variables: docs/commands.md
  Daemon HTTP routes: docs/daemon-api.md
  Config fields: docs/configuration.md

EDITING THIS FILE

  Reader has no checkout; resolve each doc path through the rule above, never a relative link.
  Context only, never mechanism, repo internals, or a command/config field/workflow another doc owns.

Attribution

ashugaevashugaev
View sourceSee grades on GitHubMore from ashugaev →
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 →