attack SKILL.md skillA
attack from donald-ada/workinggenius is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add donald-ada/workinggenius/attack@git:20261003.51d9739Pins git:20261003.51d9739 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- donald-ada/workinggenius
- Path
skills/attack/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261003.51d9739, committed Oct 3, 2026
- First version recorded
- Oct 3, 2026
- Size
- 2,783 bytes
- Repository stars
- 6
- License
- MIT
Put a plan, a design or a set of approaches the user hands over under blind attack, one attacker per path, and report what broke each and what each survived. User-invoked only, and outside the flow, so nothing is tracked and no work file is written.
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
# Attack Discernment's attack, without the flow around it. Its failure mode is the one `/discern` exists for: a plausible-but-wrong plan going ahead because nobody tried to kill it, here on a plan that was never tracked and never will be. The concept: **the paths the user names go to blind attackers, and the user gets back the wounds with their evidence, not a verdict dressed as one.** What an attack is, why each path gets its own fresh attacker, and why what comes back is a claim until checked against the repo are `/discern`'s, in [../discern/SKILL.md](../discern/SKILL.md). This command takes them from there whole; what differs is only what surrounds the attack. ## How it runs 1. Read what the user handed over and name each path in it, one line each. Where it holds one plan, that plan is the one path, because a lone plan is attacked as hard as a favourite. Where what the attack must land against is unclear (what the plan is for, how they will judge it worked), ask that in one round with a recommendation each, because an attacker handed no success criteria attacks the wrong thing. …
Read the whole file at its exact version.
How to install
mdr add donald-ada/workinggenius/attack@sha256:d52e0b1e3c7a88f2The line at the top of this page pins the label git:20261003.51d9739, 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.
[](https://markdownregistry.com/a/art_7gq4vkfuhowx5fp6)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Oct 3, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261003.51d9739 latest | 2026-10-03 | 51d9739 | 2,783 B | A | view · diff |
| git:20261003.1b3586a | 2026-10-03 | 1b3586a | 2,787 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2783 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
donald-ada/workinggenius · 6 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7gq4vkfuhowx5fp6 GET https://markdownregistry.com/api/v1/resolve?ref=donald-ada/workinggenius/attack GET https://markdownregistry.com/api/v1/blob/d52e0b1e3c7a88f204e81c65cf3c2fc5cb95f557fbb9e4e7a3669d5783824e45
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 donald-ada/workinggenius
Every file in donald-ada/workinggenius