vibetags: Skill for Claude Code

.claude/skills/consultation-loop/SKILL.md

consultation-loop is a skill for Claude Code from PIsberg/vibetags. It costs 102 tokens per session (790 once invoked), scanned A, original, MIT.

A pre-push review process in which a fresh reviewer questions the current branch's code changes. It asks whether the work is complete, production-ready, scalable, secure, and exposed to major risks.

In plain words
What is it for?
Use it before pushing a branch to get an advisory review of the diff, identify risks, and decide what should be fixed before creating a pull request.
Why use it?
A reviewer without memory of writing the code can challenge assumptions the author may overlook. Each answer must point to evidence in the change or say that the evidence is unavailable.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

This is PIsberg/vibetags's own configuration. It tells Claude Code how to work on vibetags itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything vibetags configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PIsberg/vibetags. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PIsberg/vibetags/main/.claude/skills/consultation-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PIsberg/vibetags

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 consultation-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/pisberg/vibetags/consultation-loop.svg)](https://agentmods.dev/skills/pisberg/vibetags/consultation-loop)
Your own site
<a href="https://agentmods.dev/skills/pisberg/vibetags/consultation-loop"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/consultation-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 790 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 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 $0.00102 $0.00790
Opus 5 $0.00051 $0.00395
Sonnet 5 $0.00020 $0.00158
Haiku 4.5 $0.00010 $0.00079

Measured 7d ago against content hash 126be3f61f79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

consultation-loop 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 7d 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.

.claude/skills/consultation-loop/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consultation loop

A voluntary pre-push interrogation of the branch diff. The reviewer must be a fresh context that did not produce the change: spawn a subagent (or a fresh claude -p session) and give it only the diff and the questions below. Never answer these questions from the session that wrote the code; a session reviewing its own work confirms its own assumptions.

This loop is advisory. It produces ranked findings for the author to weigh, not a verdict. The blocking review is CI's job (tests, self-check, the Inquisitor); this one exists to catch what you can still fix cheaply, before the PR exists.

Procedure

  1. Compute the diff scope: git diff origin/main...HEAD (after git fetch origin main).

  2. Spawn a fresh reviewer with the framing: "You did not write this code. Assume the author took shortcuts. Answer each question for this diff only. Every claim cites a file:line from the diff; if the diff cannot answer, say 'cannot tell from here' and name what evidence would answer it. Do not reassure."

  3. Ask the five questions, one at a time, each with its scope clause:

    1. Are we done? Enumerate what the task promised (the issue, the spec, the PR body draft) as a list, and mark each item present or absent in the diff. Done-ness is a list, not a feeling.
    2. Is it production ready? Error handling on the failure paths the diff introduces; logging of the decisions it takes (domain.event key=value, reason= on skips); behavior when its inputs are absent or malformed. Fail closed and loud.
    3. Does it scale? Algorithmic findings visible in the diff itself (per-element work inside per-file loops, unbounded accumulation, repeated I/O). Demand the distinction between "this is quadratic, see line N" and "cannot tell from here; needs a measurement" - for the latter, load-tests/ is the harness.
    4. Is it secure? What new untrusted input does this diff accept, and where does that input cross into generated files, shell commands, or paths? For this repo the classic surface is annotation string values reaching generated guardrail files; Escape.java and MarkerInjectionTest are the precedents to check against.
    5. Top three change requests, ranked by risk reduced, each citing a line. No line, no vote.

Read the full file on GitHub · 54 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. 7d ago First seen · 54 lines · 102 tokens per session scan A 126be3f61f79

Subscribe to this mod's changes

consultation-loop is a skill published in the GitHub repository PIsberg/vibetags (15 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 790 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 2026-08-30.

Related

Other skills, from other repositories

mulch-record-from-evidence

Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.

jayminwest/mulch · 61 tokens

pr-reviewer

Fetches PR review comments, analyzes requested changes, implements fixes, commits and pushes the resolution. Use after a reviewer has left comments on an open PR to close the feedback loop efficiently.

Fu-Jie/openwebui-extensions · 41 tokens

plugin-code-review-orchestrated

Orchestrates a code review of the spring-plugin repository through scope/context passes, routing, domain reviewer subskills, and per-artifact validation. Use when asked to review a PR, diff, commit, branch, module, or file set, to run a full orchestrated review, or to produce a validated review report.

explyt/spring-plugin · 72 tokens

review-ui-leak-via-listeners

Normative reviewer for memory leaks where UI components or view classes are retained by listeners on properties of long-lived services (APP/Project) or by strong references in singletons (object, companion object, static fields). Use when reviewing tool-window panels, settings pages, dialogs, wizard steps, or any code…

explyt/spring-plugin · 99 tokens

056-design-avoid-breaking-changes

Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…

jabrena/plinth · 106 tokens

review-scope-resolver

Normalizes a PR, diff, commit, branch, file list, directory, module, class, or function into an exact review target with semantic clusters and routing signals for domain reviewer subskills. Use as the first pass of an orchestrated code review, when asked to resolve review scope, or when a raw review reference must be…

explyt/spring-plugin · 83 tokens