retrieval-reflex

retrieval-reflex is a skill for Claude Code, Codex from cynthiajones34/GBrain. It costs 24 tokens per session (601 once invoked), scanned A, a copy of retrieval-reflex, MIT.

A retrieval rule that tells an agent when to open a stored knowledge page about a person, company, project, deal, place, or other important entity before answering.

In plain words
What is it for?
Use it to verify names, history, status, decisions, and other non-trivial details about entities during a conversation.
Why use it?
It reduces guesses based on memory when relevant information already exists in the knowledge base. It focuses retrieval on important mentions instead of loading everything.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to verify names, history, status, decisions, and other non-trivial details about entities during a conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cynthiajones34/gbrain/retrieval-reflex
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add cynthiajones34/GBrain --skill retrieval-reflex
Clone the repo
git clone --depth 1 https://github.com/cynthiajones34/GBrain

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for retrieval-reflex

README.md
[![agentmods](https://agentmods.dev/badge/skills/cynthiajones34/gbrain/retrieval-reflex/github.svg)](https://agentmods.dev/skills/cynthiajones34/gbrain/retrieval-reflex)
Your own site
<a href="https://agentmods.dev/skills/cynthiajones34/gbrain/retrieval-reflex"><img src="https://agentmods.dev/badge/skills/cynthiajones34/gbrain/retrieval-reflex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for retrieval-reflex

Your own site · 80×15
<a href="https://agentmods.dev/skills/cynthiajones34/gbrain/retrieval-reflex"><img src="https://agentmods.dev/badge/skills/cynthiajones34/gbrain/retrieval-reflex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 601 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00601
Opus 5 $0.00012 $0.00300
Sonnet 5 $0.00005 $0.00120
Haiku 4.5 $0.00002 $0.00060

Measured 9d ago against content hash dc96692b7643, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

retrieval-reflex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to retrieval-reflex — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

recipes/retrieval-reflex/skills/retrieval-reflex/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Read the full file on GitHub · 60 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 60 lines · 24 tokens per session scan A dc96692b7643

Subscribe to this mod's changes

retrieval-reflex is a skill published in the GitHub repository cynthiajones34/GBrain (0 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 601 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to retrieval-reflex, differing in 12 lines, and is treated as a copy.