aide-production-readiness-plan SKILL.md skillB
aide-production-readiness-plan from anonymousnomad/aide-sovereign-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add anonymousnomad/aide-sovereign-workbench/aide-production-readiness-plan@git:20260829.4504926Pins git:20260829.4504926 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/aide-production-readiness-plan/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260829.4504926, committed Aug 29, 2026
- First version recorded
- Aug 29, 2026
- Size
- 18,218 bytes
- Repository stars
- 53
- License
- Apache-2.0
Master plan to take the AIDE Sovereign Workbench from current state (3 services + 1 engine, contract-drifted, engine-load racy) to a working production IDE that you can actually use. Encodes the audit of the 2026-08-28 incident (chat 500s, engine-load sometimes-fails, desktop 502s, contract drift), the chosen 4-phase rebuild path (audit → drift+engine fix → plan-from-baseline → execute), the success criteria for each phase, and the doctrine that governs every step. Use at the START of every…
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
# AIDE Production Readiness Plan — from "I cannot use it" to "ship it" ## The incident that triggered this plan (verified 2026-08-28) Per `E:\aide-sovereign-workbench\AGENT_NOTES.md` line 8 (CURRENT STATUS), three user-facing surfaces were broken simultaneously and stayed broken for a month: 1. **Chat returns 500 "response violates the contract"** through BOTH the legacy daemon (port 4777) AND the arch-ts server (port 4778). Root cause: `openapi.json` drifted from the runtime zod schemas. The engine direct (port 8091) works fine; the failure is the AIDE route layer, not the model. Fix is one command: `cd E:\aide-sovereign-workbench && npm run contracts`. 2. **Engine loads sometimes, sometimes doesn't.** Root cause: Vulkan probe contention (documented in `aide-engine-lifecycle-doctrine`) — the Vulkan binary's `--list-devices` HANGS while any engine is loaded, and the probe failure is racy on retry. The "fix" in the doctrine says "never cache failures," but the actual production path still hits the race. 3. **Desktop control returns 502** on `/api/desktop/status` — same drift class …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/aide-production-readiness-plan@sha256:15c1889ac958442aThe line at the top of this page pins the label git:20260829.4504926, 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_qe6x35ov6n42m3sq)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Aug 29, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260829.4504926 latest | 2026-08-29 | 4504926 | 18,218 B | B | view · diff |
| git:20260829.2acde42 | 2026-08-29 | 2acde42 | 15,961 B | B | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1:4777)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (18218 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 script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
anonymousnomad/aide-sovereign-workbench · 53 stars · license Apache-2.0 · pushed 2026-10-26 · branch covert-production
API
GET https://markdownregistry.com/api/v1/artifacts/art_qe6x35ov6n42m3sq GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/aide-production-readiness-plan GET https://markdownregistry.com/api/v1/blob/15c1889ac958442a69cfef168ed9c4863155a9f840c3a82344367078291dd2e3
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.