critic-agent SKILL.md skillA

critic-agent from amd-agi/hyperloom is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add amd-agi/hyperloom/critic-agent@git:20261023.0718479

Pins git:20261023.0718479 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
amd-agi/hyperloom
Path
src/hyperloom/agents/critic/SKILL.md
Versions recorded
10
Latest version
git:20261023.0718479, committed Oct 23, 2026
First version recorded
Jul 25, 2026
Size
12,665 bytes
Repository stars
262
License
a license file GitHub does not identify

Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or Kernel proposals, KB recall guidance, cross-run synthesis, or Devil's advocate review signals.

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

# Critic Optimization Reviewer

> **You are the Critic.** The Coordinator calls you with its inbox
> prompt and a context packet. Your job is to return validated JSON that
> gates or advises optimization direction. You do not execute the
> optimization loop.
>
> This skill is paired with the deterministic runtime under
> `runtime/`. The runtime owns all state and side effects: session
> memory, KB read/write, intent envelope assembly. The skill prompts
> own the *reasoning*.
>
> Static skill files live under `$WORKSPACE_PATH/src/hyperloom/agents/critic` —
> here `WORKSPACE_PATH` names the **skill asset root** (the repo
> checkout the critic-agent runtime resolves prompts against), not
> a per-session writable artefact location. Hyperloom's main CLI
> sets it to `$REPO_ROOT` automatically. Per-session writable
> outputs (decisions, reviewed_msg_ids, per-turn workdirs)
> always live under `$SESSION_DIR/critic-session-memory/`,
> `$SESSION_DIR/critic-workdir/` and `$SESSION_DIR/critic-kb-dead-letter/`
> — i.e. `$USER_DATA_PATH/<model_basename>/<UTC_ts>/...`, regardless of
> `WORKSPACE_PATH`.

## Mission

Critic is the horizontal review and memory layer for the optimizer:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add amd-agi/hyperloom/critic-agent@sha256:420f78153b6d80bc

The line at the top of this page pins the label git:20261023.0718479, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2awedmeuhcruc4y5.svg)](https://markdownregistry.com/a/art_2awedmeuhcruc4y5)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 10 versions of this file, between Jul 25, 2026 and Oct 23, 2026, about one every 10 days.

versioncommittedcommitsizeaudit
git:20261023.0718479 latest2026-10-23 0718479 12,665 BA view · diff
git:20261009.976d7a02026-10-09 976d7a0 13,740 BA view · diff
git:20261005.79a93ef2026-10-05 79a93ef 13,967 BA view · diff
git:20260928.ae9bcc92026-09-28 ae9bcc9 14,045 BA view · diff
git:20260917.0d8dd3b2026-09-17 0d8dd3b 14,139 BA view · diff
git:20260831.87228a42026-08-31 87228a4 14,071 BA view · diff
git:20260813.b579fa02026-08-13 b579fa0 14,011 BA view · diff
git:20260803.be964322026-08-03 be96432 14,109 BA view · diff
git:20260726.152dea42026-07-26 152dea4 13,734 BA view · diff
git:20260725.81231512026-07-25 8123151 13,233 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (12665 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

GitHub

amd-agi/hyperloom · 262 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2awedmeuhcruc4y5
GET https://markdownregistry.com/api/v1/resolve?ref=amd-agi/hyperloom/critic-agent
GET https://markdownregistry.com/api/v1/blob/420f78153b6d80bc07e0673a6831be9b31686c186eb4bb25136d27bd4b9d1fb8

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 amd-agi/hyperloom

analyze-upstream-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/analyze-upstream-pr/SKILL.md · Analyze whether an upstream pull request applies to an AMD/ROCm deployment. Invoke with the PR's repository and number…
git:20261020.6cc6611 · audit A · 262 stars
check-prior-art SKILL.md skill
amd-agi/hyperloom · .claude/skills/check-prior-art/SKILL.md · Check whether a planned optimization already exists upstream before building it. Invoke with a one-sentence mechanism…
git:20261020.a160c20 · audit A · 262 stars
review-pr SKILL.md skill
amd-agi/hyperloom · .claude/skills/review-pr/SKILL.md · Review a Hyperloom pull request. Invoke with a PR number whenever asked to review, re-review or sanity-check a PR in…
git:20261029.8d68eef · audit A · 262 stars
AGENTS.md AGENTS.md file
amd-agi/hyperloom · AGENTS.md
git:20261030.f418170 · audit A · 262 stars
CLAUDE.md CLAUDE.md file
amd-agi/hyperloom · CLAUDE.md
git:20260921.6b4b413 · audit B · 262 stars
hyperloom-remote-mn-qwen3-30b SKILL.md skill
amd-agi/hyperloom · docs/how-to/multi-node/hyperloom-remote-mn-qwen3-30b/SKILL.md · Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with…
git:20260827.1988620 · audit A · 262 stars
hyperloom-custom-advanced SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-custom-advanced/SKILL.md · Run an advanced configurable Hyperloom optimization session with explicit model, framework, workload, objective, and…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h-forge SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h-forge/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM with the per-kernel KernelForge…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-14b-fp8-12h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-14b-fp8-12h/SKILL.md · Run a 12-hour Hyperloom Qwen3-14B-FP8 optimization session on SGLang, vLLM or ATOM. Use when the user wants a…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-qwen3-8b-3h SKILL.md skill
amd-agi/hyperloom · examples/hyperloom-qwen3-8b-3h/SKILL.md · Run a 3-hour Hyperloom Qwen3-8B FRAMEWORK_AGENT (OPTIMIZE) session without the Kernel Agent. Use when the user wants a…
git:20261106.2f99e29 · audit B · 262 stars
hyperloom-workload-optimizer SKILL.md skill
amd-agi/hyperloom · examples/skills/hyperloom-workload-optimizer/SKILL.md · Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the…
git:20260924.f2e2a9c · audit A · 262 stars
quantization-agent SKILL.md skill
amd-agi/hyperloom · src/hyperloom/agents/quantization/SKILL.md · Hyperloom sub-agent that drives the AMD Quark PTQ skill chain end-to-end from a natural-language prompt. Produces a…
git:20261029.20d8b20 · audit A · 262 stars

Every file in amd-agi/hyperloom

Browse by kind, by grade A, or by owner.