risky-changes SKILL.md skillA

risky-changes from davidondrej/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add davidondrej/skills/risky-changes@git:20260912.1dcbb2d

Pins git:20260912.1dcbb2d in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
davidondrej/skills
Path
skills/ops-and-setup/risky-changes/SKILL.md
Versions recorded
3
Latest version
git:20260912.1dcbb2d, committed Sep 12, 2026
First version recorded
Aug 19, 2026
Size
2,836 bytes
Repository stars
4,161
License
MIT

Verify assumptions before implementing large or risky changes to APIs, provider data, billing, pricing, quotas, or defaults. Use when a mistake could affect customers or the user asks if a change is safe to ship. Checks real-world impact beyond passing tests.

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

# Risky Changes

A filter once passed every test but disabled ~99% of the feature on live data. Tests check code correctness; research and live measurement check whether a change is useful.

## When this applies

Use for changes where being wrong is expensive or customer-visible:

- Public API fields, filters, or response shaping
- Dropping, transforming, or reordering upstream data
- Billing, pricing, caps, or quotas
- Defaults, thresholds, or provider request parameters
- Unverified assumptions about external data or user behavior

If unsure whether a change qualifies, apply this process.

## 1. Identify assumptions

List the assumptions the change depends on. Mark which have evidence and which are still unverified.

## 2. Research before implementing

Use available research tools and reliable sources. Investigate each distinct question separately, covering at least:

- How do leading products handle this design decision?
- What does real-world data look like: frequencies, shapes, and edge cases?
- What do users or agents actually need?
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add davidondrej/skills/risky-changes@sha256:bdb459b6c7430d85

The line at the top of this page pins the label git:20260912.1dcbb2d, 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_lpn4tcl3flmi3qi2.svg)](https://markdownregistry.com/a/art_lpn4tcl3flmi3qi2)

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

Versions

The registry has recorded 3 versions of this file, between Aug 19, 2026 and Sep 12, 2026, about one every 12 days.

versioncommittedcommitsizeaudit
git:20260912.1dcbb2d latest2026-09-12 1dcbb2d 2,836 BA view · diff
git:20260819.8494ccd2026-08-19 8494ccd 5,014 BA view · diff
git:20260819.964d5082026-08-19 964d508 5,068 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 (2836 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

davidondrej/skills · 4,161 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lpn4tcl3flmi3qi2
GET https://markdownregistry.com/api/v1/resolve?ref=davidondrej/skills/risky-changes
GET https://markdownregistry.com/api/v1/blob/bdb459b6c7430d8580b3461f18fb8ffd4a9fe88bbb6b2c6211c1463ddca2a9a8

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 davidondrej/skills

AGENTS.md AGENTS.md file
davidondrej/skills · AGENTS.md
git:20261018.03e51ca · audit A · 4,161 stars
bb-cli SKILL.md skill
davidondrej/skills · skills/agent-orchestration/bb-cli/SKILL.md · Use this when controlling bb. The bb CLI inspects and manages threads, environments, projects, machines, providers…
git:20260926.7dce66c · audit B · 4,161 stars
bb-plugins SKILL.md skill
davidondrej/skills · skills/agent-orchestration/bb-plugins/SKILL.md · Build, install, and debug bb plugins. Use when the user wants a bb plugin, a sidebar panel, a bb CLI subcommand, an…
git:20260925.cb72780 · audit A · 4,161 stars
cmux SKILL.md skill
davidondrej/skills · skills/agent-orchestration/cmux/SKILL.md · Control the cmux macOS terminal app: workspaces, panes, surfaces, browsers, notifications, settings, and hooks. Use…
git:20260925.cb72780 · audit A · 4,161 stars
codex-subagent SKILL.md skill
davidondrej/skills · skills/agent-orchestration/codex-subagent/SKILL.md · Launch OpenAI Codex CLI as a subagent (no API key). Use when delegating a self-contained coding task to Codex from…
git:20261012.bbafe9d · audit A · 4,161 stars
fable-review SKILL.md skill
davidondrej/skills · skills/agent-orchestration/fable-review/SKILL.md · Launch an independent Fable code review and return it verbatim. Use only when the user explicitly invokes /fable-review.
git:20261018.eaed515 · audit A · 4,161 stars
fable-safe-prompt SKILL.md skill
davidondrej/skills · skills/agent-orchestration/fable-safe-prompt/SKILL.md · Make minimal prompt edits to reduce false-positive refusals from Fable. Use only when the user explicitly invokes…
git:20260925.cb72780 · audit A · 4,161 stars
git-worktree SKILL.md skill
davidondrej/skills · skills/agent-orchestration/git-worktree/SKILL.md · Use Git worktrees to isolate parallel coding tasks. Use when setting up a task checkout, working in a shared repo, or…
git:20261017.47bdcda · audit A · 4,161 stars
goal-loop SKILL.md skill
davidondrej/skills · skills/agent-orchestration/goal-loop/SKILL.md · Draft /goal prompts and explain persistent agent loops. Use for goal or Ralph loops, autonomous run setup, monitoring…
git:20261018.eaed515 · audit A · 4,161 stars
gpt-review SKILL.md skill
davidondrej/skills · skills/agent-orchestration/gpt-review/SKILL.md · Launch an independent GPT-6.1-Sol Max code review and return it verbatim. Use only when the user explicitly invokes…
git:20261018.eaed515 · audit A · 4,161 stars
handoff SKILL.md skill
davidondrej/skills · skills/agent-orchestration/handoff/SKILL.md · Capture session context for a fresh agent. Use for handoffs, context limits, switching focus, ending sessions, or…
git:20260926.7dce66c · audit A · 4,161 stars
herdr SKILL.md skill
davidondrej/skills · skills/agent-orchestration/herdr/SKILL.md · Operate and coordinate AI agents in Herdr workspaces in Ghostty. Use when the user mentions Herdr or asks to inspect…
git:20261018.eaed515 · audit A · 4,161 stars

Every file in davidondrej/skills

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