run-scenario SKILL.md skillB
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
run-scenario from using-system/oddyssey is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add using-system/oddyssey/run-scenario@git:20260914.34daa72Pins git:20260914.34daa72 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- using-system/oddyssey
- Path
marketplace/oddyssey/skills/run-scenario/SKILL.md- Versions recorded
- 9
- Latest version
- git:20260914.34daa72, committed Sep 14, 2026
- First version recorded
- Aug 30, 2026
- Size
- 10,377 bytes
- Repository stars
- 10
- License
- MIT
Drive a reproducible request scenario against a locally running service - ad-hoc requests, or a stored k6 benchmark from .odd/benchmarks/ - and record it verbatim, so the telemetry it produces can be compared with a later run. Use when traffic must be generated before observing a service, when a stored k6 benchmark must be run, when an observation report needs a replayable scenario, or when verifying after a fix that the same scenario now measures better.
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
# Run a Scenario One protocol on both ends of the ODD loop: the same commands that produced the numbers in an observation report produce the numbers that verify the fix. A scenario that cannot be replayed verbatim makes before/after comparison an impression, not a measurement. **A step this package ships a script for is run, never rewritten.** The ad-hoc drive is this skill's `scripts/drive_scenario.py` (step 2); a stored benchmark's replay is `k6-guides`' `scripts/replay_benchmark.py` (`references/benchmark-replay.md`). A curl loop, a helper with a `sleep` in it, a poller written for either yields a different command each time — two runs then measure two things. ## Read by situation Steps 1 to 5 and the rules are the method; a reference is read by the block that applies, never whole: | Situation | Reference | | --- | --- | …
Read the whole file at its exact version.
How to install
mdr add using-system/oddyssey/run-scenario@sha256:436fe6175abdbdf0The line at the top of this page pins the label git:20260914.34daa72, 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_wzqehobrlilyl3lm)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 9 versions of this file, between Aug 30, 2026 and Sep 14, 2026, about one every 2 days. Its first recorded version is graded A and its latest B.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260914.34daa72 latest | 2026-09-14 | 34daa72 | 10,377 B | B | view · diff |
| git:20260910.8b8e2ed | 2026-09-10 | 8b8e2ed | 11,358 B | B | view · diff |
| git:20260907.4a987fd | 2026-09-07 | 4a987fd | 11,182 B | B | view · diff |
| git:20260906.9319867 | 2026-09-06 | 9319867 | 10,333 B | B | view · diff |
| git:20260905.1a73941 | 2026-09-05 | 1a73941 | 9,498 B | B | view · diff |
| git:20260904.d883e27 | 2026-09-04 | d883e27 | 8,179 B | B | view · diff |
| git:20260903.b39709c | 2026-09-03 | b39709c | 21,949 B | C | view · diff |
| git:20260902.fdf2ae3 | 2026-09-02 | fdf2ae3 | 17,519 B | B | view · diff |
| git:20260830.a69e708 | 2026-08-30 | a69e708 | 10,613 B | A | view |
Audit of the latest version
- fail: No link to a raw IP address (matched: http://127.0.0.1)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10377 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
using-system/oddyssey · 10 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_wzqehobrlilyl3lm GET https://markdownregistry.com/api/v1/resolve?ref=using-system/oddyssey/run-scenario GET https://markdownregistry.com/api/v1/blob/436fe6175abdbdf00aaf87bcad5b7092589905bb4556517cbc3fada3f1ff3634
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 using-system/oddyssey
Every file in using-system/oddyssey