New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Retrieval Reflex

by garrytan in garrytan/gbrain

When/what to retrieve — open the brain page for a salient entity before answering from memory.

MITAuto-check passed

Install Retrieval Reflex

skills CLI
$ npx skills add garrytan/gbrain --skill retrieval-reflex -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install garrytan/gbrain retrieval-reflex --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/garrytan/gbrain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/recipes/retrieval-reflex/skills/retrieval-reflex .claude/skills/retrieval-reflex && rm -rf skills-src

Use ~/.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/

Facts

Skill name
retrieval-reflex
GitHub stars
31k
Token cost
~735 tokens
SKILL.md length
336 words
Files
1
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

When/what to retrieve — open the brain page for a salient entity before answering from memory.

  • Works in 3 steps: Pointer / metadata. If a pointer is… → Full page. When the entity is the… → Linked neighbors. Only when relationship…
  • SKILL.md covers Trigger policy — WHEN to…, Retrieval spec — WHAT to pull,… and The failure this prevents
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Retrieval Reflex is an agent skill from garrytan/gbrain. When/what to retrieve — open the brain page for a salient entity before answering from memory.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Garry's Opinionated OpenClaw/Hermes Agent Brain. The licence is MIT.

Example prompts

  • “/retrieval-reflex”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Pointer / metadata. If a pointer is already in context (slug + one-line
  2. Full page. When the entity is the subject or details matter, open it
  3. Linked neighbors. Only when relationship context is needed, pull

What it can do on your machine

Read from SKILL.md and the folder at commit fc54831. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Retrieval Reflex loads about 735 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~735

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from garrytan/gbrain at commit fc54831, republished under its MIT licence (© garrytan). 336 words, ~735 tokens.

Download SKILL.mdSave it as .claude/skills/retrieval-reflex/SKILL.md (or your agent's skills folder).
name
retrieval-reflex
description
When/what to retrieve — open the brain page for a salient entity before answering from memory.
version
0.1.0
triggers
a named entity becomes the subject of the exchange, a brain-page pointer appeared in context, about to assert a detail about an entity from memory
mutating
false
writes_pages
false
tools
get_page, query, traverse_graph, get_backlinks

Retrieval Reflex — retrieve on demand, when an entity is salient

A person doesn't bulk-load their whole address book into working memory. They retrieve on demand, when an entity becomes salient, use it, and drop it. Encode that reflex. The brain probably has the data — if a name is salient and you haven't opened its page, open it before you answer.

Trigger policy — WHEN to retrieve

Retrieve when ANY of these holds AND the page isn't already loaded in context:

  • An entity (person / company / project / deal / place) is the subject of the message, or a decision/judgment about it is being made, or the exchange is substantive / relational / emotional about it.
  • A brain-page pointer appeared in context this turn (the deterministic layer told you the page exists) — open it before relying on details.
  • A name or term appears that you don't recognize and that looks notable → do a quick resolve (the human reflex).
  • You're about to assert a non-trivial detail about an entity (attribution, status, history) → verify against the brain first. Say "let me check", not a guess.

Skip trivial passing mentions, logistics pings, and anything already loaded. Judgment first — retrieve when it changes the quality of the reply, not reflexively.

Retrieval spec — WHAT to pull, and when to stop

Escalate only as far as the task needs:

  1. Pointer / metadata. If a pointer is already in context (slug + one-line summary), and the task only needs identity, stop there.
  2. Full page. When the entity is the subject or details matter, open it: get_page <slug> (MCP) — read the page before relying on specifics.
  3. Linked neighbors. Only when relationship context is needed, pull graph / backlinks for the slug.

Resolve only the name(s) the current task needs, use them, drop them. No bulk-loading the inner circle.

The failure this prevents

If you've discussed a named person for more than a message without opening their page, open it now. The write side captures everything; the read side only helps if you actually look.

See also: skills/query/SKILL.md (search the brain), skills/brain-ops/SKILL.md.

© garrytan, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in recipes/retrieval-reflex/skills/retrieval-reflex of garrytan/gbrain.

Open the folder on GitHubat commit fc54831

Compare with similar skills

Retrieval Reflex 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.

Retrieval Reflex compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Retrieval Reflex this skillgarrytan/gbrain31k—~735Automated safety check: PassMIT
Iterative Retrievalaffaan-m/ECC276k7 repos~1.6kAutomated safety check: PassMIT
Brainjeremylongshore/tons-of-skills-marketplace2.8k—~1.9kAutomated safety check: PassApache-2.0
Twenty Syncable Entity Cache and Transformtwentyhq/twenty58k—~2.4kAutomated safety check: PassCustom licence
Iterative Retrievalaffaan-m/ECC276k2 repos~1.1kAutomated safety check: PassMIT
Iterative Retrievalaffaan-m/ECC276k2 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Iterative Retrieval

    affaan-m/ECC

    Pattern for progressively refining context retrieval to solve the subagent context problem.

    276k GitHub starsUsed in 7 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Brain

    jeremylongshore/tons-of-skills-marketplace

    Answers questions about your own systems, notes, decisions, runbooks, and conventions from your governed knowledge brain, returning a qmd:// citation for every claim — receipts, not recall.

    2.8k GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check passed

  • Twenty Syncable Entity Cache and Transform

    twentyhq/twenty

    Walks through step 2 of adding a syncable entity to the Twenty server: a cache service for flat entity maps and utilities that transform entities and DTOs into universal flat entities.

    58k GitHub stars~2.4k tokensUpdated today
    Backend & APIsAuto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    サブエージェントのコンテキスト問題を解決するために、コンテキスト取得を段階的に洗練するパターン. An agent skill from affaan-m/ECC.

    276k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴. An agent skill from affaan-m/ECC.

    276k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    逐步优化上下文检索以解决子代理上下文问题的模式

    276k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

More from garrytan/gbrain

All 47 skills in this repo

  • Correction Root-Cause Pipeline

    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.

    31k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Company Knowledge Brain

    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.

    31k GitHub stars~875 tokensUpdated today
    Auto-check passed

  • Idea Ingest

    garrytan/gbrain

    Ingest links, articles, tweets, and ideas into the brain. An agent skill from garrytan/gbrain.

    31k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Brain-Augmented Web Research

    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.

    31k GitHub stars~2k tokensUpdated today
    Auto-check: notes

  • Schema Unify

    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.

    31k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Skillpack Check

    garrytan/gbrain

    Run gbrain skillpack-check to produce an agent-readable JSON health report for the gbrain install.

    31k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Questions about Retrieval Reflex

What does Retrieval Reflex do?

When/what to retrieve — open the brain page for a salient entity before answering from memory. Retrieval Reflex is an agent skill from garrytan/gbrain. When/what to retrieve — open the brain page for a salient entity before answering from memory.

How do I install Retrieval Reflex in Claude Code?

Run `npx skills add garrytan/gbrain --skill retrieval-reflex -a claude-code`. Or copy the skill folder (recipes/retrieval-reflex/skills/retrieval-reflex in garrytan/gbrain) into .claude/skills/retrieval-reflex in your project. Claude Code loads it when a task matches its description.

How do I install Retrieval Reflex in Codex?

Run `npx skills add garrytan/gbrain --skill retrieval-reflex -a codex`. Or copy the skill folder (recipes/retrieval-reflex/skills/retrieval-reflex in garrytan/gbrain) into .agents/skills/retrieval-reflex in your project. Codex loads it when a task matches its description.

Can I use Retrieval Reflex in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add garrytan/gbrain --skill retrieval-reflex -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/retrieval-reflex, .gemini/skills/retrieval-reflex, .github/skills/retrieval-reflex and .opencode/skills/retrieval-reflex in your project.

What does Retrieval Reflex need to run?

SKILL.md names no scripts, command-line tools or credentials: Retrieval Reflex is instructions for the agent only.

Does Retrieval Reflex access the network?

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.

Is Retrieval Reflex safe to install?

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.

What licence does Retrieval Reflex use?

Retrieval Reflex is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Retrieval Reflex use?

About 735 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Retrieval Reflex?

Skills that share tags, products or a category with Retrieval Reflex: Iterative Retrieval (affaan-m/ECC, 276k stars), Brain (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Twenty Syncable Entity Cache and Transform (twentyhq/twenty, 58k stars) and Iterative Retrieval (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Retrieval Reflex?

garrytan (a GitHub user) maintains it in garrytan/gbrain, which has 30,701 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 9, 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.