discriminator SKILL.md skillA
discriminator from kalabint/llm-tooling is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kalabint/llm-tooling/discriminator@git:20260907.47ea7d2Pins git:20260907.47ea7d2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kalabint/llm-tooling
- Path
skills/discriminator/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260907.47ea7d2, committed Sep 7, 2026
- Size
- 4,858 bytes
- Repository stars
- 6
- License
- AGPL-3.0
Guard against attribute substitution on any output that will be acted on as a verdict, ranking, routing, or go/no-go decision — regardless of how the request is phrased. Casual-looking prompts ("where does this stand?", "predict the path") are the highest-risk, so do NOT gate on apparent analytical register; gate on decision stakes. Also invoke when an earlier answer keeps getting corrected and re-pivoting one level too shallow.
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
# Discriminator
Attribute substitution: when a question is hard ("which sessions actually needed Opus?"), the model swaps it for a cheaper one it can answer ("which openers look complex?") and reports the substitute's answer with confidence calibrated to the substitute, not the real target. The "you're right, let me use a better signal" recovery is the same failure in a new coat — it swaps one proxy for a slightly better proxy under correction pressure, still one level too shallow, and the loop repeats.
## What this skill actually does — read this first
It does **not** make the model correct itself. Substitution is invisible to the substituting process at the moment it happens — if the model could see the swap, it wouldn't make it. So the steps below can themselves be performed *as substitutes*: a plausible target/proxy/gap that is itself shallow, a soft counterexample engineered to conveniently survive. The ritual runs; the swap passes underneath.
…Read the whole file at its exact version.
How to install
mdr add kalabint/llm-tooling/discriminator@sha256:0329b851b19f5110The line at the top of this page pins the label git:20260907.47ea7d2, 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_u3ht6mnyrvkhpzcy)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 7, 2026.
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 (4858 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
kalabint/llm-tooling · 6 stars · license AGPL-3.0 · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_u3ht6mnyrvkhpzcy GET https://markdownregistry.com/api/v1/resolve?ref=kalabint/llm-tooling/discriminator GET https://markdownregistry.com/api/v1/blob/0329b851b19f51101dc9166d75d179163a01fe06cb7afd4bc1da6db4f1f13d4b
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.