think

think is a skill for Claude Code from matteotitta/genesys-skills. It costs 190 tokens per session (2,976 once invoked), scanned A, original, MIT.

A recall skill for answering questions about when events happened and how information changed over time. It searches dated project history, goals, memory pages, and session decisions, then arranges the results chronologically.

In plain words
What is it for?
It answers questions such as when something last happened, what changed since an earlier point, and what the latest update is.
Why use it?
It reduces the need to manually search scattered historical notes when finding the latest status or reconstructing a timeline.

Skill for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: built for gbrain.

Good fit It answers questions such as when something last happened, what changed since an earlier point, and what the latest update is.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/matteotitta/genesys-skills/think
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 matteotitta/genesys-skills --skill think
Clone the repo
git clone --depth 1 https://github.com/matteotitta/genesys-skills

Made for: Claude Code.

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 think

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteotitta/genesys-skills/think/github.svg)](https://agentmods.dev/skills/matteotitta/genesys-skills/think)
Your own site
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/think"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/think/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 think

Your own site · 80×15
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/think"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/think.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 190 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,976 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00190 $0.02976
Opus 5 $0.00095 $0.01488
Sonnet 5 $0.00038 $0.00595
Haiku 4.5 $0.00019 $0.00298

Measured 10d ago against content hash d8c1e8ab6acc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

think 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 10d 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.

skills/meta/session/think/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/think — Temporal-trajectory queries against the brain

Answer "when did X last Y" / "what changed since Z" / "what's the latest on W" by splicing dated entries from client history.md, sprint goals/MMYY-NN-cycle.md, memory pages, and session decisions into a chronological timeline. Zero LLM cost on intent classification — regex routes the query, the splice does the work.

Stolen from garrytan/gbrain (v0.40.2.0) via /steal Phase 5–6 (2026-05-23). See .claude/discovery/0526-gbrain-steal-analysis.md item G19.


Triggers

Invoke this skill when the user says:

  • /think [question]
  • "When did Alan last push back on positioning?"
  • "When was the last time we shipped a Pulse?"
  • "What changed in ClientCo's pricing since the March doc?"
  • "What's the latest on ClientCo's GTM stack build?"
  • "Any new on ClientCo?"
  • "What happened with the Notion shadow-pull thing?"

Do NOT invoke when:

  • The question is rule-shaped or convention-shaped ("do we have a rule about X?") — use /recall --memory
  • The question is decision-extraction shaped ("what did we decide about X?") — use /recall --decisions
  • The question is research-shaped or external ("what's Salesloft launching this week?") — follow .claude/rules/brain-first-lookup.md then Exa per exa-protocol.md
  • The question is in-session reasoning ("what should we do next?") — just answer

If unsure between /think and /recall: /think is for when-shaped and what-changed-shaped questions; /recall is for what-was-decided and what-was-discussed questions.


Process

Step 1 — Classify intent (regex, zero-LLM)

Apply the classifier to the input question. Three intents:

Intent Regex pattern (case-insensitive) Routing
temporal `\b(when last time
knowledge_update `\b(latest recent
other (no match) Fast-path: short-circuit to /recall <topic>

Read the full file on GitHub · 227 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. 10d ago First seen · 227 lines · 190 tokens per session scan A d8c1e8ab6acc

Subscribe to this mod's changes

think is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 190 tokens to every session and 2,976 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gingiris-b2b-growth

🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF. PLG/SLG selection by ACV and sales cycle, the 5-stage path from $0 to $10M ARR, NRR discipline, affiliate & channel motion, enterprise tiering. Built from HeyGen, Deel, Vercel, Supabase, Snowflake patterns.…

Gingiris-1031/gingiris-skills · 484 tokens

go-to-market-playbook

A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.

Gingiris-1031/gingiris-skills · 48 tokens

gr-b2b-growth

A guide to growing a business-to-business software product from early user research to large-scale sales. B2B software is sold to companies rather than individual consumers.

Gingiris-1031/gingiris-skills · 83 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

add-editor

Wire Deus's memory + evolution layers into an external code editor (Zed and other ACP/MCP clients) so the editor's own agent gains Deus's vault recall and self-improving reflexion loop. Configuration only — no new code. Triggers on "add editor", "use Deus in my editor", "zed integration", "editor integration", "wire…

sliamh11/Deus · 89 tokens

resume

Load context from permanent memory and recent session logs. Tiered loading — CLAUDE.md full, session logs frontmatter-only by default.

sliamh11/Deus · 30 tokens