context-tax-audit SKILL.md skillA

context-tax-audit from minimax-ai/mcode-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add minimax-ai/mcode-stack/context-tax-audit@git:20261029.49a3ff4

Pins git:20261029.49a3ff4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
minimax-ai/mcode-stack
Path
stacks/ronny/skills/context-tax-audit/SKILL.md
Versions recorded
2
Latest version
git:20261029.49a3ff4, committed Oct 29, 2026
First version recorded
Oct 28, 2026
Size
3,714 bytes
Repository stars
495
License
MIT

Inventory everything an agent injects into each request besides the user's message, such as system prompt, environment info, skill list, tool definitions, per-turn context blocks and reminders, and check necessity, frequency, precision, position and prompt-cache impact. Use when reviewing an agent's prompt assembly, chasing low cache hit rates, or trimming per-turn overhead.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Context Tax Audit

Every request carries more than the user's sentence: system prompt,
environment info, the skill list, tool definitions, per-turn context blocks,
reminders. Most of it is worth paying for. The audit finds what is not, and
what is placed so that it breaks the prompt cache.

Companion to MCode Engineering Notes 05 (how the agent learns the
current time — and why stuffing `date` into the system prompt breaks the
prefix cache).
Plain-text checklist: `checklists/context-tax.md`.

## 1. Inventory one real request

Capture an actual request the agent sends (debug log, proxy, or the code that
assembles it). List every part except the user's message:

| Part | Where it sits | How often it changes | Tokens |
| --- | --- | --- | --- |

Count tokens with a tokenizer and name it; treat the counts as relative.
Do a fresh-session first request and a later turn, since they often differ.

## 2. Necessity - what breaks if you delete it?

For each part, write one sentence: "without this, the model would ...".
Typical answers: without environment info it guesses the OS and shell; without
the current time it assumes its training year; without a time budget it does
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add minimax-ai/mcode-stack/context-tax-audit@sha256:afd253b0ba4b1328

The line at the top of this page pins the label git:20261029.49a3ff4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4xrv26pb75rsyon3.svg)](https://markdownregistry.com/a/art_4xrv26pb75rsyon3)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Oct 28, 2026 and Oct 29, 2026, about one every 2 days.

versioncommittedcommitsizeaudit
git:20261029.49a3ff4 latest2026-10-29 49a3ff4 3,714 BA view · diff
git:20261028.c889a192026-10-28 c889a19 3,636 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3714 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

minimax-ai/mcode-stack · 495 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4xrv26pb75rsyon3
GET https://markdownregistry.com/api/v1/resolve?ref=minimax-ai/mcode-stack/context-tax-audit
GET https://markdownregistry.com/api/v1/blob/afd253b0ba4b132826388d2c6c55c3de52693d05e21a961e1cd8fe918c58b53a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from minimax-ai/mcode-stack

lifting-loops SKILL.md skill
minimax-ai/mcode-stack · stacks/jiachen/skills/lifting-loops/SKILL.md · Finds loops where the user keeps acting as a manual step for agents (retrying, judging output, approving, carrying…
git:20261028.e7307b0 · audit A · 495 stars
making-content SKILL.md skill
minimax-ai/mcode-stack · stacks/jiachen/skills/making-content/SKILL.md · Content production in three modes: rewrite, Xiaohongshu (小红书) image post, short video. Rewrite (default): turns an…
git:20261028.e7307b0 · audit A · 495 stars
engineering-change-descriptions SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-change-descriptions/SKILL.md · Use when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain…
git:20261028.c6ee606 · audit A · 495 stars
engineering-code-review SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-code-review/SKILL.md · Use when reviewing code, pull requests, patches, CLs, diffs, or proposed implementations for engineering quality, code…
git:20261028.c6ee606 · audit A · 495 stars
engineering-emergency-changes SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-emergency-changes/SKILL.md · Use when a code hotfix, rollback alternative, production/security/legal fix, launch blocker, or hard external deadline…
git:20261028.c6ee606 · audit A · 495 stars
engineering-review-comments SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-review-comments/SKILL.md · Use when drafting, rewriting, classifying, or improving code review comments as a reviewer. TRIGGER on rough review…
git:20261028.c6ee606 · audit A · 495 stars
engineering-review-feedback SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-review-feedback/SKILL.md · Use when handling code review feedback as the change author, addressing reviewer comments, drafting replies, resolving…
git:20261028.c6ee606 · audit A · 495 stars
engineering-small-prs SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-small-prs/SKILL.md · Use when planning, splitting, shrinking, or sequencing large features, refactors, migrations, or pull requests into…
git:20261028.c6ee606 · audit A · 495 stars
handoff-doc SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/handoff-doc/SKILL.md · Write a hand-off document so a fresh session or another person can continue the current task without the chat history…
git:20261028.c889a19 · audit A · 495 stars
harness-experiment SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/harness-experiment/SKILL.md · Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and…
git:20261029.49a3ff4 · audit A · 495 stars
independent-review SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/independent-review/SKILL.md · Review a code change from a clean context, the way an outside reviewer would. Use after the agent finishes an…
git:20261028.c889a19 · audit A · 495 stars
long-command-check SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/long-command-check/SKILL.md · Audit how an agent harness runs long shell commands, covering foreground wait limits, moving to background without…
git:20261028.c889a19 · audit A · 495 stars

Every file in minimax-ai/mcode-stack

Browse by kind, by grade A, or by owner.