gameplay-harness SKILL.md skillA
gameplay-harness from jammyfu/open-game-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jammyfu/open-game-skills/gameplay-harness@git:20261026.7da3509Pins git:20261026.7da3509 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jammyfu/open-game-skills
- Path
skills/disciplines/gameplay-harness/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261026.7da3509, committed Oct 26, 2026
- First version recorded
- Sep 13, 2026
- Size
- 8,023 bytes
- Repository stars
- 12
- License
- MIT
Use when a game needs an executable driver beside the runtime to inject semantic inputs, replay deterministic tapes, step the project's existing logic clock, and collect inspectable evidence. It does not decide what a session proves, replace game QA, or create a second gameplay clock.
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
# Gameplay harness Use this skill to **drive and observe** a game build. Stack `gameplay-validation` to decide what the resulting session may prove, `game-qa` to decide which QA column is required, and `gameplay-capture` for video/edit provenance. ## Ownership This skill owns: - input tape schema and driver mode - adapter probes into the game runtime - deterministic replay orchestration - session/evidence identity - stable oracle comparison It does **not** own: - evidence/claim taxonomy (`gameplay-validation`) - QA coverage taxonomy (`game-qa`) - capture/edit truthfulness (`gameplay-capture`) - hitstop, damage, hitboxes, AI, save rules, or other gameplay semantics - a new fixed timestep ## Driver modes Ask for one driver mode: | Driver mode | Driver | Required classification behavior | |---|---|---| | logic | fixture/function inputs | usually supports `logic-regression`; claim still comes from `gameplay-validation` | | replay | committed semantic tape | supports deterministic regression only for the recorded scope | | scripted | tape plus explicit setup overrides | forces `scripted-scene` evidence classification | …
Read the whole file at its exact version.
How to install
mdr add jammyfu/open-game-skills/gameplay-harness@sha256:d016583eb436d1ecThe line at the top of this page pins the label git:20261026.7da3509, 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_mgrcikhfj3o45t3c)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 13, 2026 and Oct 26, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.7da3509 latest | 2026-10-26 | 7da3509 | 8,023 B | A | view · diff |
| git:20260914.6145d0a | 2026-09-14 | 6145d0a | 7,708 B | A | view · diff |
| git:20260913.0c047b1 | 2026-09-13 | 0c047b1 | 7,284 B | A | view · diff |
| git:20260913.f28f7a2 | 2026-09-13 | f28f7a2 | 6,715 B | A | view · diff |
| git:20260913.23d3443 | 2026-09-13 | 23d3443 | 3,375 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 (8023 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
jammyfu/open-game-skills · 12 stars · license MIT · pushed 2026-11-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mgrcikhfj3o45t3c GET https://markdownregistry.com/api/v1/resolve?ref=jammyfu/open-game-skills/gameplay-harness GET https://markdownregistry.com/api/v1/blob/d016583eb436d1eca88dc4d3a5cf5066c254ae7de1a54188151d57b0ab41ca88
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.