incremental-safety SKILL.md skillA

incremental-safety from rlaope/ultraprompt is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rlaope/ultraprompt/incremental-safety@git:20260915.a5ced99

Pins git:20260915.a5ced99 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rlaope/ultraprompt
Path
skills/incremental-safety/SKILL.md
Versions recorded
2
Latest version
git:20260915.a5ced99, committed Sep 15, 2026
First version recorded
Jul 5, 2026
Size
13,109 bytes
Repository stars
35
License
MIT

Decompose a large or risky change into a sequence of independently safe intermediate states, so the system stays green at every step and any step can be reverted alone.

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

# Incremental Safety

> Status: v0.1 baseline draft — derived from the case catalog and axis definitions; awaiting trace evidence from Fable 5.1 case runs.

## When to apply

- The change touches 3+ files, crosses a module boundary, or alters a public interface, schema, or wire format.
- You are migrating between technologies (framework swap, storage engine, protocol version) while the system must keep running.
- The change cannot be verified in one shot — the test suite, a benchmark, or production traffic is the only real oracle.
- Rollback matters: the target runs in production, other agents or humans work on the same tree, or the deploy is not atomic.
- A refactor started as "small" but the diff keeps growing and you have not committed anything runnable yet.
- You are about to do a big-bang rewrite and cannot state what proves the rewrite behaves identically to the original.

## Core loop

1. **Name the end state and the invariant.** Write one sentence for the target and one for what must stay true throughout,
   e.g. "all existing tests pass", "API responses byte-identical", "p99 within 5% of baseline".
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rlaope/ultraprompt/incremental-safety@sha256:1f64f6c4cf342eea

The line at the top of this page pins the label git:20260915.a5ced99, 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_jmcpfdriryhjyyo3.svg)](https://markdownregistry.com/a/art_jmcpfdriryhjyyo3)

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

Versions

The registry has recorded 2 versions of this file, between Jul 5, 2026 and Sep 15, 2026, about one every 72 days.

versioncommittedcommitsizeaudit
git:20260915.a5ced99 latest2026-09-15 a5ced99 13,109 BA view · diff
git:20260705.c12b4fc2026-07-05 c12b4fc 13,107 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 (13109 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

rlaope/ultraprompt · 35 stars · license MIT · pushed 2026-10-28 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jmcpfdriryhjyyo3
GET https://markdownregistry.com/api/v1/resolve?ref=rlaope/ultraprompt/incremental-safety
GET https://markdownregistry.com/api/v1/blob/1f64f6c4cf342eeac0156aca252019b3bb2c043e7436dcdeba6713779c1d7cc3

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 rlaope/ultraprompt

context-memory-hygiene SKILL.md skill
rlaope/ultraprompt · skills/context-memory-hygiene/SKILL.md · Invoke when deciding what to load into context, what to persist across turns or sessions, and what to drop — reads only…
git:20260915.a5ced99 · audit A · 35 stars
delegation-parallelism SKILL.md skill
rlaope/ultraprompt · skills/delegation-parallelism/SKILL.md · Invoke when deciding whether to split work across parallel agents/sessions or do it inline — tests scope independence…
git:20260915.a5ced99 · audit A · 35 stars
exploration-strategy SKILL.md skill
rlaope/ultraprompt · skills/exploration-strategy/SKILL.md · Build an accurate mental model of an unfamiliar codebase or problem before making any edit — structural scan…
git:20260915.a5ced99 · audit A · 35 stars
failure-mode-enumeration SKILL.md skill
rlaope/ultraprompt · skills/failure-mode-enumeration/SKILL.md · Systematically enumerate how code can break — boundaries, concurrency, partial failure, malicious input, time, resource…
git:20260915.a5ced99 · audit A · 35 stars
honest-reporting SKILL.md skill
rlaope/ultraprompt · skills/honest-reporting/SKILL.md · Invoke when writing any status, completion, or result report — calibrates claims to the evidence actually gathered…
git:20260915.a5ced99 · audit A · 35 stars
hypothesis-management SKILL.md skill
rlaope/ultraprompt · skills/hypothesis-management/SKILL.md · Debug by maintaining 2-4 competing hypotheses with explicit evidence and kill criteria, choosing each probe to…
git:20260915.a5ced99 · audit A · 35 stars
self-correction-loop SKILL.md skill
rlaope/ultraprompt · skills/self-correction-loop/SKILL.md · Invoke when an implementation attempt produces a failure signal (test failure, compile error, wrong output, crash, perf…
git:20260915.a5ced99 · audit A · 35 stars
spec-to-code-fidelity SKILL.md skill
rlaope/ultraprompt · skills/spec-to-code-fidelity/SKILL.md · Invoke when implementing from an authoritative written source — an RFC, academic paper, binary format spec, protocol…
git:20260915.a5ced99 · audit A · 35 stars
state-probing SKILL.md skill
rlaope/ultraprompt · skills/state-probing/SKILL.md · Invoke before acting on any assumption about the runtime or environment — versions, running processes, file/disk…
git:20260915.a5ced99 · audit A · 35 stars
tradeoff-articulation SKILL.md skill
rlaope/ultraprompt · skills/tradeoff-articulation/SKILL.md · Invoke when a design decision has multiple viable implementations and the choice affects performance, memory…
git:20260915.a5ced99 · audit A · 35 stars
verification-discipline SKILL.md skill
rlaope/ultraprompt · skills/verification-discipline/SKILL.md · Invoke before claiming any task is done — defines what counts as evidence of completion (execution, not inspection) and…
git:20260915.a5ced99 · audit A · 35 stars

Every file in rlaope/ultraprompt

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