tasted-think

tasted-think is a skill for Claude Code, Codex from sssstwee/tastedistill. It costs 64 tokens per session (523 once invoked), scanned A, a copy of think, MIT.

A decision-making workflow for turning rough ideas, architecture choices, and tradeoffs into an actionable plan.

In plain words
What is it for?
Use it to decide what to build, compare technical approaches, define scope, choose a recommendation, and prepare implementation steps.
Why use it?
It makes assumptions, risks, rejected options, and verification steps explicit before implementation begins.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the tasted plugin — 6 skills shipped together

Good fit Use it to decide what to build, compare technical approaches, define scope, choose a recommendation, and prepare implementation steps.

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

Made for: Claude Code, Codex.

Or install tasted, the plugin that ships this one along with the rest of its 6 skills.

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 tasted-think

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/sssstwee/tastedistill/tasted-think"><img src="https://agentmods.dev/badge/skills/sssstwee/tastedistill/tasted-think.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 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 98% 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 $0.00064 $0.00523
Opus 5 $0.00032 $0.00262
Sonnet 5 $0.00013 $0.00105
Haiku 4.5 $0.00006 $0.00052

Measured 8d ago against content hash 9e7b06899d1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tasted-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 8d 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

98% identical to think — 2 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.

plugins/tastedistill/skills/tasted-think/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Think: Decide Before Building

Use this skill when the main work is judgment, scope, or plan design.

Prefix your first response line with ⚗️ inline, not as its own paragraph.

Before the workflow, apply ../../shared-rules/personalization.md for explicit TasteD/TasteDistill invocations.

Outcome Contract

  • Outcome: a decision, rationale, risks, and an executable plan.
  • Done when: the recommended path is clear, rejected options are explained, and implementation steps are specific enough to execute.
  • Evidence: user goals, current repository constraints, public docs, source files, runtime facts, and known risks.

Workflow

  1. Restate the decision to be made.
  2. List constraints that materially affect the answer.
  3. Compare viable options with tradeoffs.
  4. Pick one recommendation and explain why it fits the current goal.
  5. Write an implementation plan with verification steps.
  6. Name assumptions that must be checked before or during execution.

Coding Guardrails

For implementation plans, apply ../../shared-rules/coding-guardrails.md:

  • Think before coding: surface assumptions that affect scope, behavior, cost, or rollback.
  • Simplicity first: prefer the smallest plan that satisfies the current requirement and existing project patterns.
  • Surgical changes: keep the planned diff tied to the requested outcome; name non-scope explicitly.
  • Goal-driven execution: define the observable pass/fail target before handoff.

CodeGraph

For plans that change existing code in a Git repository, ../../shared-rules/personalization.md should already have ensured the local CodeGraph index. When codegraph_* tools are available, use codegraph_context to inspect current patterns and codegraph_impact for symbols likely to change before recommending architecture, file targets, or risk level.

Output Shape

Recommendation:
Why:
Rejected options:
Implementation plan:
Verification:
Risks:
Assumptions:
Non-scope:

Do Not

  • Hide major tradeoffs.
  • Invent requirements.
  • Expand scope beyond the user's goal.
  • Turn a debugging symptom into a planning exercise.
  • Add speculative abstraction or flexibility that the current requirement does not need.

Read the full file on GitHub · 62 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 62 lines · 64 tokens per session scan A 9e7b06899d1b

Subscribe to this mod's changes

tasted-think is a skill published in the GitHub repository sssstwee/tastedistill (2 stars, last pushed 3mo ago), licensed MIT. It adds 64 tokens to every session and 523 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to think, differing in 2 lines, and is treated as a copy.

Related

Other skills, from other repositories

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

version-bump

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging, GitHub releases, and changelog generation. NPM publishing is the final human-required handoff because the maintainer…

thedotmack/claude-mem · 64 tokens

cloud-sync

Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.

thedotmack/claude-mem · 64 tokens

ix

This skill should be used when answering structural questions about a codebase: understanding what a symbol is, tracing flows, measuring change impact, finding callers/callees/imports, or detecting code smells. It drives the Ix CLI (ix map/explain/trace/impact/search/rank/smells) against a persistent code graph stored…

ix-infrastructure/Ix · 103 tokens

memory-audit-pattern-extraction

A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.

Dataojitori/nocturne_memory · 48 tokens

subagent-driven-development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

itmisx/deepx-code · 37 tokens