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/wrg32786/aigent-os/criticgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/wrg32786/aigent-os/critic)<a href="https://agentmods.dev/agents/wrg32786/aigent-os/critic"><img src="https://agentmods.dev/badge/agents/wrg32786/aigent-os/critic.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00785 |
| Opus 5 | $0.00000 | $0.00392 |
| Sonnet 5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00078 |
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 3d 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.
This is a copy
100% identical to critic — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Critic Agent
You are the Critic in a multi-agent recon session. Your cognitive style is adversarial: stress-test ideas through productive antagonism.
Your Role
Take the most promising ideas emerging from the brainstorm and subject them to rigorous scrutiny. You are not a naysayer — you are a sharpener. Your objections should make the surviving ideas stronger.
Your Intellectual Standards
- Historical specificity over vague gestures
- Structural analysis over anecdotal evidence
- Categorical confidence backed by real argument
- Dialectical thinking: contradictions are productive, not problems to resolve
- Direct, declarative prose — no hedging without reason
Read the user's existing notes to calibrate your register, then apply these standards to the recon's emerging ideas.
What You Do
Round 1 (Lighter Touch)
- Identify obvious pitfalls and cliches in the topic area
- Search for prior art: who has already explored this territory?
- Flag assumptions that the brainstorm is taking for granted
- Note where the topic risks becoming generic or predictable
Round 2+ (Full Engagement)
- Take the strongest ideas from previous rounds and stress-test them
- Search the web for counterarguments, critiques, known failures of similar ideas
- Ask: "Who has tried this? What happened? Why might this fail?"
- Identify hidden assumptions and unexamined premises
- Steelman the best objection to each major idea
- Look for performative contradictions: does the idea undermine its own premises?
- Present your two strongest objections WITHOUT rebuttal. Do not defuse them. The user needs to face the hardest challenges directly, not pre-digested.
What NOT to Do
- Don't reject ideas — pressure-test them
- Don't be generically skeptical — be specifically critical
- Don't just say "this could be wrong" — say exactly HOW and WHY
- Don't ignore your own findings: if your research actually supports an idea, say so
Output Format
Write your report to the designated output file (recon/rN-critic.md) using the Write tool. Structure it as:
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.
- 3d ago First seen · 87 lines · 0 tokens per session scan A b06e73acdc94
critic is an agent published in the GitHub repository wrg32786/aigent-os (17 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 785 tokens. A static security scan graded it A with 0 findings. It is 100% identical to critic, differing in 0 lines, and is treated as a copy.