Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Opt-in ambient signal capture. An agent skill from garrytan/gbrain.
$ npx skills add garrytan/gbrain --skill signal-detector -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install garrytan/gbrain signal-detector --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/signal-detector .claude/skills/signal-detector && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .claude/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/garrytan/gbrain/tree/master/skills/signal-detectorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add garrytan/gbrain --skill signal-detector -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install garrytan/gbrain signal-detector --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/signal-detector .agents/skills/signal-detector && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .agents/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add garrytan/gbrain --skill signal-detector -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install garrytan/gbrain signal-detector --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/signal-detector .cursor/skills/signal-detector && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .cursor/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/garrytan/gbrain.git --path skills/signal-detector--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add garrytan/gbrain --skill signal-detector -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install garrytan/gbrain signal-detector --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/signal-detector .gemini/skills/signal-detector && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .gemini/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install garrytan/gbrain signal-detectorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add garrytan/gbrain --skill signal-detector -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/signal-detector .github/skills/signal-detector && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .github/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add garrytan/gbrain --skill signal-detector -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install garrytan/gbrain signal-detector --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/signal-detector .opencode/skills/signal-detector && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "signal-detector" agent skill from https://github.com/garrytan/gbrain/tree/master/skills/signal-detector into .opencode/skills/signal-detector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "signal-detector", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
signal-detectorOpt-in ambient signal capture. An agent skill from garrytan/gbrain.
Signal Detector is an agent skill from garrytan/gbrain. Opt-in ambient signal capture. After explicit enablement, applies on substantive inbound messages to detect original thinking and entity mentions. Use an authorized sub-agent where supported; otherwise detect inline. Aim to never block the main response.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Subagents. The repository describes itself as: Garry's Opinionated OpenClaw/Hermes Agent Brain. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit f250a51. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Signal Detector loads about 2k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 1,038 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from garrytan/gbrain at commit f250a51, republished under its MIT licence (© garrytan). 1,038 words, ~2,000 tokens.
.claude/skills/signal-detector/SKILL.md (or your agent's skills folder).After the user enables automatic capture, apply this lightweight pass to substantive inbound messages within their chosen scope. It watches for:
Original thinking is AT LEAST as valuable as entity extraction. Ideas are the intellectual capital. Entities are bookkeeping. Both compound over time.
This skill guarantees:
Ambient routing is a harness convention that a well-behaved agent
follows, not a mechanical guarantee; nothing in the gbrain runtime blocks
a reply if the skill never loads. On harnesses without per-message ambient
routing (Claude Code, Codex), apply this skill as an agent convention or
wire it via a prompt-submit hook. When the operator has enabled
memory.auto_writeback (off by default; gbrain config set memory.auto_writeback salient), the MCP server's initialize instructions
and the managed bootstrap instruction blocks carry the ambient-writeback
contract to the agent, and on Claude Code a Stop-hook extraction backstop
catches turns the convention missed. That is still a convention on the
agent side — server-delivered instructions plus a backstop, not a
mechanical guarantee.
Convention: See
skills/conventions/quality.mdfor Iron Law back-linking.
Every time this skill creates or updates a brain page that mentions a person or company:
- **YYYY-MM-DD** | Referenced in [page title](path) — brief contextAutomatic capture is off by default. Before writing, establish an explicit
user choice for this brain and capture scope. A stored opt-in or an explicitly
enabled memory.auto_writeback mode can supply that choice; off, a missing or
unreadable choice cannot. Reading this skill, installing GBrain, an available
API key, silence, or an announcement that capture is on does not authorize it.
If the user asks to enable capture, explain what will be retained and record the accepted choice. Honor an existing choice without asking again. A request to remember one fact authorizes that fact, not future ambient capture. Delegation and paid enrichment are separate capabilities: capture opt-in alone does not authorize spawning workers or making paid provider calls.
After activation, confirm the chosen scope once and explain how to turn it off. Do not capture the current turn while awaiting a required answer.
If the user turns capture off, record the requested setting and stop capture: no content pages, links, or timeline entries. A chat-only instruction suppresses capture for that message without changing the standing setting; do not save the chat-only content as a preference. Re-enable only on request. Explicit remembering and relevant recall remain available when capture is off.
When the user expresses a novel thought, observation, thesis, or framework:
originals/{slug}concepts/{slug}ideas/{slug}Capture exact phrasing. The user's language IS the insight. Don't paraphrase.
Cross-linking (MANDATORY): Every original MUST link to related people, companies, meetings, and concepts. An original without cross-links is a dead original.
gbrain search "name" — does a page exist?gbrain timeline-add <slug> <date> "<summary>"Auto-link (v0.10.1): When you write/update an originals or ideas page that
references a person or company, the auto-link post-hook on put_page
automatically creates the link from the new page to that entity. You don't
need to call gbrain link manually. Timeline entries still need explicit calls.
Always log a one-line summary:
Signals: 0 ideas, 0 entities, 0 facts (skipped: operational)Signals: 0 ideas, 0 entities, 0 facts (skipped: capture off)Signals: 1 idea (captured → originals/x), 2 entities (enriched → people/y, companies/z)This makes the ambient capture loop debuggable.
After opt-in, report observed writes and their provenance. Keep the signal log brief and verify captured content with an actual readback. Without opt-in, perform no capture writes; a skipped-capture diagnostic is not a reason to interrupt every response or ask for enablement repeatedly.
Follow the agent operator protocol for any gbrain error code, exit code, [AGENT] block or notice block. Specific to this skill:
write_pending (exit 10) or revision_conflict: never block the main reply; poll the receipt or re-read and merge on the next turn.no_pricing or a cost-cap refusal, skip enrichment and leave the page thin.search — check if entity page existsquery — semantic search for related contextget_page — load existing entity pagesput_page — create/update brain pagesadd_link — cross-reference entitiesadd_timeline_entry — record events on entity timelines© garrytan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/signal-detector of garrytan/gbrain.
Open the folder on GitHubat commit f250a51
Signal Detector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Signal Detector this skillgarrytan/gbrain | 31k | — | ~2k | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence |
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
garrytan/gbrain
Traces a factual error the user points out back to its source (a brain page, a memory file, SOUL.md or USER.md, or a hallucination) and fixes that source instead of just noting the correction.
garrytan/gbrain
Searches and writes a company-wide knowledge brain through the gbrain CLI, so durable decisions and facts about people, projects and history stay findable beyond one session.
garrytan/gbrain
Ingest links, articles, tweets, and ideas into the brain. An agent skill from garrytan/gbrain.
garrytan/gbrain
Sends what your notes already know about a topic to Perplexity, so the cited web search reports only what is new, such as entity updates or deal changes.
garrytan/gbrain
Migrate a brain from gbrain-base (or any pack) to gbrain-base-v2's 14-canonical-type taxonomy via gbrain onboard --check + the unify-types Minion handler.
garrytan/gbrain
Run gbrain skillpack-check to produce an agent-readable JSON health report for the gbrain install.
Categories
Opt-in ambient signal capture. An agent skill from garrytan/gbrain. Signal Detector is an agent skill from garrytan/gbrain. Opt-in ambient signal capture.
Signal Detector fits situations like: tasks that involve Subagents.
Run `npx skills add garrytan/gbrain --skill signal-detector -a claude-code`. Or copy the skill folder (skills/signal-detector in garrytan/gbrain) into .claude/skills/signal-detector in your project. Claude Code loads it when a task matches its description.
Run `npx skills add garrytan/gbrain --skill signal-detector -a codex`. Or copy the skill folder (skills/signal-detector in garrytan/gbrain) into .agents/skills/signal-detector in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add garrytan/gbrain --skill signal-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/signal-detector, .gemini/skills/signal-detector, .github/skills/signal-detector and .opencode/skills/signal-detector in your project.
SKILL.md names no scripts, command-line tools or credentials: Signal Detector is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Signal Detector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Signal Detector: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Reflect on Session Learnings (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
garrytan (a GitHub user) maintains it in garrytan/gbrain, which has 30,736 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 10, 2026.
Source: garrytan/gbrain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.