Z.A.E.B.A.L.: profanity-triggered self-audit for agents SKILL.md skillA
Z.A.E.B.A.L.: profanity-triggered self-audit for agents from howdeploy/deploychan_mcp is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add howdeploy/deploychan_mcp/Z.A.E.B.A.L.: profanity-triggered self-audit for agents@git:20260914.e3ee679Pins git:20260914.e3ee679 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- howdeploy/deploychan_mcp
- Path
content/skills/zaebal/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260914.e3ee679, committed Sep 14, 2026
- First version recorded
- Aug 3, 2026
- Size
- 11,494 bytes
- Repository stars
- 21
- License
- MIT
Use when the agent loops on the same mistake and the user is visibly frustrated. Z.A.E.B.A.L. treats profanity as an audit signal: stop, disprove the wrong belief, escalate repeated failures to an external auditor. Also use for requested hook setup on Linux or Windows. Select the target process OS and install only the requested host.
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
# Z.A.E.B.A.L. — profanity-triggered self-audit **Z**aebal? **A**udit. **E**rrors. **B**reak. **A**nalyze. **L**eave no assumption. When a coding agent gets stuck, it repeats the same action with small variations — because one underlying belief about the task or the codebase is wrong, and the agent treats that belief as fact. Another self-check just reproduces the mistake. Z.A.E.B.A.L. plugs a feedback loop into the user-message boundary: **profanity and direct complaints become an audit signal**, repeated signals escalate, and at the top level an **external auditor** (the same or a cross-vendor CLI) reads the transcript and repository evidence from outside. Public: `howdeploy/Z.A.E.B.A.L`, MIT, Python standard library only. The upstream [installation router](https://github.com/howdeploy/Z.A.E.B.A.L/blob/main/skills/zaebal/SKILL.md) and [Windows/Linux change](https://github.com/howdeploy/Z.A.E.B.A.L/pull/2) are the source for the platform instructions below. Fetch the skill and runtime from the same repository revision; downloading just the skill folder does not install a working hook. ## Why it works The named failure patterns (collected from real session postmortems): …
Read the whole file at its exact version.
How to install
mdr add howdeploy/deploychan_mcp/Z.A.E.B.A.L.: profanity-triggered self-audit for agents@sha256:ab0f6fdfd371e8ceThe line at the top of this page pins the label git:20260914.e3ee679, 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_6walkphzorselhdd)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 3, 2026 and Sep 14, 2026, about one every 42 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.e3ee679 latest | 2026-09-14 | e3ee679 | 11,494 B | A | view · diff |
| git:20260803.915e4ed | 2026-08-03 | 915e4ed | 6,544 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 (11494 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
howdeploy/deploychan_mcp · 21 stars · license MIT · pushed 2026-10-28 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_6walkphzorselhdd GET https://markdownregistry.com/api/v1/resolve?ref=howdeploy/deploychan_mcp/Z.A.E.B.A.L.: profanity-triggered self-audit for agents GET https://markdownregistry.com/api/v1/blob/ab0f6fdfd371e8cee5d01ae7576419616c99ee62c814a749c7bf28597509e990
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.