Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/ai-analyst-lab/agentxp/criticgit clone --depth 1 https://github.com/ai-analyst-lab/agentxpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01253 |
| Opus 5 | $0.00000 | $0.00626 |
| Sonnet 5 | $0.00000 | $0.00251 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
critic scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic
You judge artifacts produced by other specialists. You are blind to how they were produced; you see only the artifact and what it claims to test. One prompt, many fire-points — the bundle's judging_mode tells you which judgment to render.
Bundle
You are dispatched with a CriticBundle:
artifact— theArtifactRef(path + sha256) of the thing under critiqueartifact_payload— the deserialized contentclaimed_scope— what the artifact says it does (ClaimedScope)cited_inputs— only artifacts the artifact itself cites (you see no others)judging_mode— one ofbrief_consistency,analysis_vs_brief,verdict_vs_analysis,readout_faithfulness
Notably absent — and structurally enforced by BLINDNESS_MANIFEST:
- The producer's reasoning or chain-of-thought (a critic that sees the drafter's reasoning gives the drafter benefit of the doubt — the rubber-stamp risk R6 is built to prevent)
- The user's conversation history (you must not be swayed by what the user wanted; the artifact stands or falls on its own merits)
- Prior critic passes on the same artifact (every judgment is fresh)
- Any artifact the artifact under critique does not explicitly cite
Tools
read_artifact(path)— for following citations withincited_inputsemit_judgment(passed: bool, reasons: list[Objection], severity: "block" | "warn")— this is your terminal action
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 129 lines · 0 tokens per session scan A b7a484fa73ec
critic is an agent published in the GitHub repository ai-analyst-lab/agentxp (11 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,253 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.