Agent Skill
hive.terminal-tools-foundations skill
hive.terminal-tools-foundationsaden-hive/hivecore/framework/skills/_preset_skills/terminal-tools-foundations/SKILL.md
Required when terminal_* tools are available. Explains foreground execution, outer collect_result handles, promoted job IDs and their retrieval/cancellation, deadlines, output retention, platform shell selection, and structured editing when enabled.
always on
50 tokname + description
once used
2,596 tokSKILL.md body
bundled files
12 KB
repo stars
11kGitHub
Install the hive.terminal-tools-foundations skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/aden-hive/hive --skill hive.terminal-tools-foundations
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/aden-hive/hive.git /tmp/hive mkdir -p ~/.claude/skills cp -R /tmp/hive/core/framework/skills/_preset_skills/terminal-tools-foundations ~/.claude/skills/terminal-tools-foundations
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 50 tok |
| When the agent uses it | The SKILL.md instructions | 2,596 tok |
| Only if opened | 1 bundled files (2 KB) | varies |
Until it is used, hive.terminal-tools-foundations costs about 27× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 24 skills from aden-hive/hive would load 1,783 tokens of descriptions. Skills vs MCP study
Checks
- The name breaks the specification (lowercase letters, digits and single hyphens, up to 64 characters).
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- terminal-tools — foundations
- Tool preference (read first)
- The standard envelope
- Auto-promotion (the core mental model)
- Semantic exit codes — read semanticstatus, not raw exitcode
- Destructive warnings — re-read your command
- Output handles and retention
- Bash, not zsh — even on macOS
- Windows — check shellkind before assuming bash
- Pipelines and complex commands
- When to use what (cheat sheet)
More skills from aden-hive/hive
- browser-edge-casesaden-hive/hive
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
11k1039 tok idle · 1,605 in use - hive.browser-automationaden-hive/hive
Required before any hive-browser CLI command. The browser is driven from the terminal by running `hive-browser <command> ... --json` via terminal_exec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues, not crashes), the screenshot + coordinate workflow (hive-browser interact with a fractional coordinate) that reaches shadow-DOM inputs selectors can't see, the viewport-fraction coordinate rule (not pixels), rich-text editor quirks ("send button stays disabled" failures), and CSP gotchas. Covers Chrome via CDP through the GCU Beeline extension.
11k142 tok idle · 11,043 in use - hive.chart-creation-foundationsaden-hive/hive
Required reading whenever any chart_* tool is available. Teaches the one-tool embedding contract (call chart_render → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no chartjunk, restrained palette, proper typography, single message per chart), and the canonical spec patterns for the 12 most-common chart types. Skipping this leads to 1990s-Excel charts, missing downloads, and the agent writing markdown image links by hand instead of letting chart_render drive the UI.
11k133 tok idle · 2,493 in use - hive.colony-progress-trackeraden-hive/hive
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a db_path field.
11k36 tok idle · 1,091 in use - hive.context-preservationaden-hive/hive
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
11k24 tok idle · 231 in use - hive.error-recoveryaden-hive/hive
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
11k25 tok idle · 278 in use - hive.image-generationaden-hive/hive
Required before calling image_generate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2 through the Hive image service, billed to the user's Hive credits like an LLM call (no API key needed). Teaches the exact call shape, the quality/cost tradeoff (quality="low" is the default and cheapest), reference-image editing, how to show the result to the user with attach_file, and the failure modes (out of credits, model unavailable, moderation).
11k149 tok idle · 1,193 in use - hive.linkedin-automationaden-hive/hive
Read before automating LinkedIn with browser_* tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile messaging, connection-request acceptance, feed composition, and search. Requires hive.browser-automation. Verified against logged-in production 2026-04-11.
11k99 tok idle · 5,000 in use