harness-first SKILL.md skillA
harness-first from getedgehq/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add getedgehq/skills/harness-first@git:20260916.370373dPins git:20260916.370373d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- getedgehq/skills
- Path
harness-first/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260916.370373d, committed Sep 16, 2026
- First version recorded
- Sep 16, 2026
- Size
- 4,769 bytes
- Repository stars
- 5
- License
- Apache-2.0
Diagnose and fix an unreliable, expensive, or unsafe LLM agent by auditing its harness (golden set, judge, cost caps, data layer, action approvals, tracing) before blaming or swapping the model. Use when someone says an agent is "burning tokens", "hallucinating", "brittle", gives inconsistent answers, asks whether to switch to a cheaper/better model, or wants to ship an agent or prompt change to customers.
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
# Harness first A model is an engine. Most "model problems" are a missing harness: nothing defines a correct output, nothing checks changes, nothing caps spend, the data has no agreed definitions, actions have no approval, and there are no traces to find the bad call. Audit that before touching the model. ## 1. Reproduce the symptom from evidence, not vibes - Read the agent code the symptom touches: the loop, tool definitions, prompt assembly, data access, side-effecting tools. - Read whatever logs/traces/transcripts exist. Aggregate them (per conversation, per tool, per error): who spends the tokens, which calls fail, which answers are wrong. A few outliers usually dominate. - State the root cause as a mechanism with evidence (file:line, log ids, numbers you computed). "The model is bad" is not a mechanism. Common mechanisms: - **Token burn:** loop with no max-iterations, retry on a deterministic error, full history or a huge tool result resent every turn, no caching of stable context. …
Read the whole file at its exact version.
How to install
mdr add getedgehq/skills/harness-first@sha256:a8bba75560a67a93The line at the top of this page pins the label git:20260916.370373d, 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_n4nt5kr2twiovjyu)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 16, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260916.370373d latest | 2026-09-16 | 370373d | 4,769 B | A | view · diff |
| git:20260916.ef32acf | 2026-09-16 | ef32acf | 4,756 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 (4769 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
getedgehq/skills · 5 stars · license Apache-2.0 · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_n4nt5kr2twiovjyu GET https://markdownregistry.com/api/v1/resolve?ref=getedgehq/skills/harness-first GET https://markdownregistry.com/api/v1/blob/a8bba75560a67a937f48be98883c08bf3c5efacacf9dbba90ffca2f5f300fef3
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.