implementation-loop SKILL.md skillA
implementation-loop from olddonkey/olddonkey-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add olddonkey/olddonkey-skills/implementation-loop@git:20261016.b947628Pins git:20261016.b947628 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- olddonkey/olddonkey-skills
- Path
skills/implementation-loop/SKILL.md- Versions recorded
- 8
- Latest version
- git:20261016.b947628, committed Oct 16, 2026
- First version recorded
- Aug 17, 2026
- Size
- 30,146 bytes
- Repository stars
- 17
- License
- MIT
Delegate implementation to Codex or to a sandboxed Claude Code (`claude -p`), have a model from the other vendor review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex or a sandboxed Claude to write code, mentions handing off / delegating implementation to one of those backends, asks for a cross-vendor review of delegated code, asks to work through a plan or spec unit-by-unit with an implementation backend doing the…
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
# Implementation loop **One model writes the code, a model from another vendor reviews it, and you own the judgment.** The implementer (Codex, or Claude Code in a sandboxed copy) is fast at implementation but it self-reports success, cannot commit, and will hang a machine if pointed at a long test suite. You give it a precise spec, make sure the review comes from a different vendor than the code, then be the thing that actually verifies and ships: you read the diff, run the gate, and publish. Both directions work: Codex implements and you review, or the claude backend implements and Codex cross-reviews. What matters is that the writer and the reviewer are different models. **This includes bug fixes**: a bug found at review, at the gate, or later is a unit like any other — you diagnose and spec, the implementer implements. Editing code directly "because it's faster" silently inverts the division of labor and costs review its independence. The loop: **decompose → dispatch → review (yours, plus a cross-review when the writer is your own vendor) → iterate → gate → publish → next**. ## Non-negotiables …
Read the whole file at its exact version.
How to install
mdr add olddonkey/olddonkey-skills/implementation-loop@sha256:3835d4fec39190caThe line at the top of this page pins the label git:20261016.b947628, 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_xrmlusnswo444cz2)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 8 versions of this file, between Aug 17, 2026 and Oct 16, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261016.b947628 latest | 2026-10-16 | b947628 | 30,146 B | A | view · diff |
| git:20261016.c3f7329 | 2026-10-16 | c3f7329 | 32,145 B | A | view · diff |
| git:20261005.fd01b10 | 2026-10-05 | fd01b10 | 29,899 B | A | view · diff |
| git:20260928.6644aca | 2026-09-28 | 6644aca | 29,627 B | A | view · diff |
| git:20260928.720828a | 2026-09-28 | 720828a | 28,773 B | A | view · diff |
| git:20260818.f052f79 | 2026-08-18 | f052f79 | 28,098 B | A | view · diff |
| git:20260817.fe72613 | 2026-08-17 | fe72613 | 27,592 B | A | view · diff |
| git:20260817.c698ac4 | 2026-08-17 | c698ac4 | 27,561 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 (30146 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
olddonkey/olddonkey-skills · 17 stars · license MIT · pushed 2026-10-16 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xrmlusnswo444cz2 GET https://markdownregistry.com/api/v1/resolve?ref=olddonkey/olddonkey-skills/implementation-loop GET https://markdownregistry.com/api/v1/blob/3835d4fec39190ca999a28ab22c5cc3ddf62194de47ed1cd2ae9ea526275ac6b
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.