Home / rjmurillo / ai-agents · GitHub

avoiding-manufactured-work SKILL.md skillA

avoiding-manufactured-work from rjmurillo/ai-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add rjmurillo/ai-agents/avoiding-manufactured-work@v1.1.0

Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: rjmurillo/ai-agents
Path: .claude/skills/avoiding-manufactured-work/SKILL.md
Versions recorded: 5
Latest version: v1.1.0, committed Sep 25, 2026
First version recorded: Jun 2, 2026
Size: 5,757 bytes
Repository stars: 48
License: MIT

Detect and stop manufactured work after a deliverable appears done, and classify a post-completion finding into the four contract classes builder-ethos.md delegates here. Use when a worker has produced a plan, issue, PR, backlog item, research artifact, or follow-up task and you need to verify it was demanded by a real user, acceptance criterion, or blocked decision instead of reward-seeking activity.

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

# Avoiding Manufactured Work

Detect follow-up work that exists because the agent wanted to keep helping, not because a real consumer asked for it.

## Sibling skill

Pair this with the `front-gate-before-pipeline` pattern. Front-gate fires before work begins; this skill fires after work appears done. Same root cause (skipping self-evaluation under reward bias), opposite timing.

## Triggers

`is this work manufactured`, `does this follow-up have a consumer`, `classify this post-completion finding`, `should I file this follow-up`

## Process

1. Name the concrete work product under review.
2. Identify the consumer: user, issue, acceptance criterion, failing check, reviewer thread, or blocked downstream decision.
3. If no consumer exists, stop. Do not create a task, issue, PR, memo, or research artifact.
4. If a consumer exists, verify the proposed follow-up is the smallest action that unblocks that consumer.
5. Report the disposition as one of: keep, shrink, defer, or delete.

## Decision Rules

- Keep work that directly satisfies an acceptance criterion, fixes a failing required check, resolves a reviewer thread, or unblocks a named decision.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add rjmurillo/ai-agents/avoiding-manufactured-work@sha256:5566cf33bae424a2

The line at the top of this page pins the label v1.1.0, 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](https://markdownregistry.com/badge/art_kvfssf5symsakom3.svg)](https://markdownregistry.com/a/art_kvfssf5symsakom3)

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

Versions

The registry has recorded 5 versions of this file, between Jun 2, 2026 and Sep 25, 2026, about one every 29 days.

version	committed	commit	size	audit
v1.1.0 latest	2026-09-25	3fda96c	5,757 B	A	view · diff
v1.1.0	2026-09-15	9a1694e	5,550 B	A	view · diff
v1.1.0	2026-09-05	fa0b025	4,414 B	A	view · diff
v1.0.0	2026-07-22	e05dfd8	1,853 B	A	view · diff
v1.0.0	2026-06-02	35c9cd1	1,878 B	A	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 (5757 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

rjmurillo/ai-agents · 48 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kvfssf5symsakom3
GET https://markdownregistry.com/api/v1/resolve?ref=rjmurillo/ai-agents/avoiding-manufactured-work
GET https://markdownregistry.com/api/v1/blob/5566cf33bae424a2618371296b4b01fe995a385831411b80abd87dc0d007c957

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.