gut-check

gut-check is a skill for Claude Code, Codex from technicalpickles/pickled-claude-plugins. It costs 106 tokens per session (890 once invoked), scanned A, original, MIT.

A checking guide for decisions and factual claims made during coding work. It asks you to ground important conclusions instead of relying on memory or an unchecked first impression.

In plain words
What is it for?
Use it before important decisions, user questions, or claims that something is fixed, tested, found, or understood.
Why use it?
It reduces mistakes caused by committing to a hard-to-reverse choice or claiming that work is complete without enough evidence.

Skill for Claude CodeCodex

Part of the gut-check plugin — 1 skill shipped together

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.

agentmods
npx agentmods add skills/technicalpickles/pickled-claude-plugins/gut-check
Any agent
npx skills add technicalpickles/pickled-claude-plugins --skill gut-check
Clone the repo
git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins

Made for: Claude Code, Codex.

Or install gut-check, the plugin that ships this one along with the rest of its 1 skill.

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 gut-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/gut-check.svg)](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/gut-check)
Your own site
<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/gut-check"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/gut-check.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 890 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00106 $0.00890
Opus 5 $0.00053 $0.00445
Sonnet 5 $0.00021 $0.00178
Haiku 4.5 $0.00011 $0.00089

Measured 5d ago against content hash 17b5e8daa81f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gut-check 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 5d 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.

plugins/gut-check/skills/gut-check/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gut Check

The spine

Don't lock in a decision or assert a fact from a thin basis: memory, the handoff, the first framing, an unexamined pick. Ground it first, then proceed.

Violating the letter of this is violating the spirit of it. "I'm confident, so I can skip the check" is the exact failure this skill exists to catch.

When this fires

You are about to do one of these AND the basis is thin (not verified this session):

  • Lock in a non-trivial or hard-to-reverse decision
  • Fire AskUserQuestion to offload a decision you could ground yourself
  • Proceed on your own preferred option without weighing alternatives
  • Assert something is done / found / tested / fixed / "that's how X works"

Skip it for trivial, reversible steps, and for claims already backed by output you produced this turn. When unsure whether it's trivial, it isn't, engage.

Shared opening (both modes)

Name the thin basis in one line: "I'm about to [decide X / claim Y] based on [memory / the handoff / first framing / my own pick]." Naming it is what flips you from asserting to grounding.

Then pick the mode: grounding a decision → DECIDE. Grounding a fact → VERIFY.

DECIDE mode

  1. Validity gate. For each option, is it even real/valid? Drop the bogus ones.
  2. Consult existing context. Read the relevant ADRs, docs, code, prior decisions. The answer is often already settled there, don't reason in a vacuum.
  3. Per-option tradeoffs. One by one: pros/cons, plus effort (easier/harder) and durability (long-run). Not a blurry summary.
  4. Ranked recommendation. State a lean and why, give something to react to.
  5. Hand the call back. Surface the recommendation; let the user decide. Do the thinking; don't offload the thinking, and don't seize the deciding.

VERIFY mode

  1. State the claim precisely. "I'm claiming X is done/found/true."
  2. Check it this session. Read the file, run the command, grep the evidence. Memory and the handoff do not count.
  3. Report grounded. "Confirmed, here's the evidence" / "No, not actually done" / "Partial: X yes, Y no." Show the receipt.

Read the full file on GitHub · 80 lines

Files

What ships with it

4 files 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. 5d ago First seen · 80 lines · 106 tokens per session scan A 17b5e8daa81f

Subscribe to this mod's changes

gut-check is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 890 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

project-memory

Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.

ur-grue/autopunk-media-skills · 31 tokens

project-retrospective

Generate a LESSONS.md from a finished project: what worked, what didn't, what to reuse, what to retire — formatted for next-project carry-over.

ur-grue/autopunk-media-skills · 37 tokens

template-selector

Recommend the right skill bundle, agent, and workflow sequence for a new project — so media professionals can start producing instead of browsing a 394-skill library.

ur-grue/autopunk-media-skills · 35 tokens

absolute-simplify

Use when the user wants to simplify, clean up, refactor, tidy, or refine code — their staged/unstaged git changes or a target file/path. Reduces complexity, flattens nesting, removes redundancy and dead code, scores each change by value (holding low-value churn), then runs tests to prove nothing broke. Invoke on…

maddhruv/absolute · 178 tokens

absolute-ui

Build polished, intentional UIs with concrete CSS/Tailwind values — typography, color, layout, spacing, dark mode, accessibility, animations, components. Encodes specific, opinionated rules with exact values, not vague advice. Covers buttons, cards, forms, tables, navigation, dashboards, landing pages, onboarding, and…

maddhruv/absolute · 121 tokens

absolute-work

End-to-end, phase-gated SDLC for AI coding agents: relentless design interview → reviewed spec → dependency-graphed task board → safe-wave TDD execution → verification → converge. Handles features, bugs, refactors, greenfield projects, planning breakdowns, and migrations. Triggers on "absolute work", "build this…

maddhruv/absolute · 104 tokens