Omh Workflow Learning
rlaope/oh-my-hermes
[omh] Missed route or run lessons to record: classify and review self-improvement store routes as an auxiliary review lane before durable writes, then record workflow attempts as metadata-only…
Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom.
Install Critic Agent
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AMD-AGI/Hyperloom critic-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/hyperloom/agents/critic .claude/skills/critic-agent && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .claude/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/criticType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AMD-AGI/Hyperloom critic-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .agents/skills && cp -r skills-src/src/hyperloom/agents/critic .agents/skills/critic-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .agents/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AMD-AGI/Hyperloom critic-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/src/hyperloom/agents/critic .cursor/skills/critic-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .cursor/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/AMD-AGI/Hyperloom.git --path src/hyperloom/agents/critic--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AMD-AGI/Hyperloom critic-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/src/hyperloom/agents/critic .gemini/skills/critic-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .gemini/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install AMD-AGI/Hyperloom critic-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .github/skills && cp -r skills-src/src/hyperloom/agents/critic .github/skills/critic-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .github/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add AMD-AGI/Hyperloom --skill critic-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AMD-AGI/Hyperloom critic-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AMD-AGI/Hyperloom.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/src/hyperloom/agents/critic .opencode/skills/critic-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "critic-agent" agent skill from https://github.com/AMD-AGI/Hyperloom/tree/main/src/hyperloom/agents/critic into .opencode/skills/critic-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "critic-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
critic-agent- GitHub stars
- 217
- Token cost
- ~3.5k tokens
- SKILL.md length
- 1,547 words
- Files
- 59 (incl. references)
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom.
- Works in 6 steps: Review Orchestration and Kernel… → For dialogue-style requests, return a… → Review benchmark, accuracy, rollback,… → …
- Conductor asks for a Critic Review verdict on Orchestration
- SKILL.md covers Mission, Two-Phase Loop, Request Types and Review Constraints, plus 3 more sections
- Runs Python scripts from its folder; calls python and git
What it does
Critic Agent is an agent skill from AMD-AGI/Hyperloom. Critic layer for the inference optimizer. Use when Conductor asks for a Critic Review verdict on Orchestration or Kernel proposals, conversation-driven decision review, KB recall/ingest guidance, cross-run synthesis, or Devil's advocate review signals.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 61 other files, including reference files (for example `README.md`, `__init__.py` and `actions/draft_kb.md`).
It sits in AI & LLM Engineering, covering Proposals and quotes. The repository describes itself as: An agentic system that auto-optimizes LLM workloads on AMD GPUs.
When your agent uses it
- Conductor asks for a Critic Review verdict on Orchestration
- Kernel proposals
- Conversation-driven decision review
- KB recall/ingest guidance
Example prompts
- “/critic-agent”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Review Orchestration and Kernel proposals with one verdict per
- For dialogue-style requests, return a critic_decision_review with
- Review benchmark, accuracy, rollback, dispatch, and cross-layer
- Own KB read/write/synthesis for cross-run memory (via the runtime).
- Emit Devil's advocate signals as advice, never as parliament votes.
- Attach predicted_gain_pct to approve and redirect verdicts for
What it can do on your machine
Read from SKILL.md and the folder at commit ea621bc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythongit
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Critic Agent loads about 3.5k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 1,547 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,547 words (~3,479 tokens).
“Critic is the horizontal review and memory layer for the optimizer:”
- name
- critic-agent
- globs
- **/critic*, **/review*, **/patch*, **/benchmark*, **/OPTIMIZATION_REPORT*, **/final_report*
Files
SKILL.md and 58 other files (references) in src/hyperloom/agents/critic of AMD-AGI/Hyperloom.
- SKILL.md
- .gitignore
- README.md
- __init__.py
- actions/draft_kb.md
- actions/objection_signal.md
- actions/review_coordinator_inbox.md
- actions/review_decision.md
- actions/review_patch.md
- references/coordinator_protocol.md
- references/decision_review_schema.md
- references/intent_envelope.md
- references/risk_rules.md
- references/verdict_schema.md
- runtime/__init__.py
- runtime/category_mapping.py
- runtime/cli.py
- runtime/dead_letter.py
- … and 41 more
Open the folder on GitHubat commit ea621bc
Compare with similar skills
Critic Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Critic Agent this skillAMD-AGI/Hyperloom | 217 | — | ~3.5k | Automated safety check: Pass | Custom licence | |
| Omh Workflow Learningrlaope/oh-my-hermes | 3.2k | — | ~2k | Automated safety check: Pass | MIT | |
| Find Simplificationsvllm-project/vllm-omni | 7.1k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| Overmind Datasetsovermind-core/overmind | 597 | — | ~875 | Automated safety check: Pass | AGPL-3.0 | |
| Qv Quality Reportingtetherto/qvac | 681 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Account ExecutiveaAAaqwq/AGI-Super-Team | 105 | 1 repos | ~3.4k | Automated safety check: Pass | MIT |
Similar skills
Find Simplifications
vllm-project/vllm-omni
Find evidence-backed simplification candidates in vLLM-Omni and, when requested, turn them into focused proposals or code changes.
Overmind Datasets
overmind-core/overmind
Build, inspect, prepare, generate and export Overmind datasets in Data Workshop.
Qv Quality Reporting
tetherto/qvac
Run the deterministic code-quality audit, turn related findings into contextual remediation groups, prepare approval-gated Asana proposals, reconcile recurring runs, or configure twice-monthly…
Account Executive
aAAaqwq/AGI-Super-Team
Expert sales execution covering pipeline management, discovery, demos, negotiation, and deal closing.
- Official
Doc Coauthoring
aws-samples/sample-strands-agent-with-agentcore
Guide users through a structured workflow for co-authoring documentation.
More from AMD-AGI/Hyperloom
Review PR
AMD-AGI/Hyperloom
Review a Hyperloom pull request. An agent skill from AMD-AGI/Hyperloom.
Hyperloom Global Kb
AMD-AGI/Hyperloom
Deploys or restarts the shared global Experience KB that Hyperloom workspaces push their Experiences to and pull others' from, validates authenticated health, and tells each workspace which .env…
Hyperloom Remote Mn Qwen3 30b
AMD-AGI/Hyperloom
Run a 4-hour multi-node Hyperloom Qwen3-30B-A3B optimization (Infera PD-disaggregated or RayJob aggregated) with --nodes 2 and sglang MoE tuning on MI325X.
Hyperloom Setup
AMD-AGI/Hyperloom
Configures Hyperloom after pip install --target . An agent skill from AMD-AGI/Hyperloom.
Related
Categories
Questions about Critic Agent
What does Critic Agent do?
Critic layer for the inference optimizer. An agent skill from AMD-AGI/Hyperloom. Critic Agent is an agent skill from AMD-AGI/Hyperloom. Critic layer for the inference optimizer.
When should I use Critic Agent?
Critic Agent fits situations like: conductor asks for a Critic Review verdict on Orchestration; kernel proposals; conversation-driven decision review; KB recall/ingest guidance.
How do I install Critic Agent in Claude Code?
Run `npx skills add AMD-AGI/Hyperloom --skill critic-agent -a claude-code`. Or copy the skill folder (src/hyperloom/agents/critic in AMD-AGI/Hyperloom) into .claude/skills/critic-agent in your project. Claude Code loads it when a task matches its description.
How do I install Critic Agent in Codex?
Run `npx skills add AMD-AGI/Hyperloom --skill critic-agent -a codex`. Or copy the skill folder (src/hyperloom/agents/critic in AMD-AGI/Hyperloom) into .agents/skills/critic-agent in your project. Codex loads it when a task matches its description.
Can I use Critic Agent in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AMD-AGI/Hyperloom --skill critic-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/critic-agent, .gemini/skills/critic-agent, .github/skills/critic-agent and .opencode/skills/critic-agent in your project.
What does Critic Agent need to run?
Going by SKILL.md and its folder, Critic Agent needs Python for the scripts in its folder and the command-line tools its instructions call (python and git). Our summary lists: Python 3.
Does Critic Agent access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Critic Agent safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Critic Agent use?
Critic Agent has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Critic Agent use?
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.2k tokens, read only when the agent opens those files.
What are the alternatives to Critic Agent?
Skills that share tags, products or a category with Critic Agent: Omh Workflow Learning (rlaope/oh-my-hermes, 3.2k stars), Find Simplifications (vllm-project/vllm-omni, 7.1k stars), Overmind Datasets (overmind-core/overmind, 597 stars) and Qv Quality Reporting (tetherto/qvac, 681 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Critic Agent?
AMD-AGI (a GitHub organization) maintains it in AMD-AGI/Hyperloom, which has 217 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: AMD-AGI/Hyperloom on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.