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 skills add xinshixu7170/independent-critic --skill independent-criticgit clone --depth 1 https://github.com/xinshixu7170/independent-criticWrote 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/skills/xinshixu7170/independent-critic/independent-critic)<a href="https://agentmods.dev/skills/xinshixu7170/independent-critic/independent-critic"><img src="https://agentmods.dev/badge/skills/xinshixu7170/independent-critic/independent-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xinshixu7170/independent-critic/independent-critic"><img src="https://agentmods.dev/badge/skills/xinshixu7170/independent-critic/independent-critic.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00049 | $0.00346 |
| Opus 5 | $0.00024 | $0.00173 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
independent-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 12d 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.
What it actually says
Have the custom agent named independent-critic review the user's target.
- Start it in a fresh context. If the current spawn tool exposes a context-history option, pass no conversation history; do not invent an unsupported parameter.
- Give it the exact target, real paths, numbered falsifiable claims, and the question “What did I miss?” Do not include the parent agent's preferred answer or reasoning.
- Choose the depth for the user instead of asking: deep for anything irreversible (shipping, migrations, permissions, deleting data, privacy), quick for routine small changes, standard otherwise. Narrow the scope to the change under review rather than the whole repository; that is the largest speed lever.
- Keep it read-only. If it requests a write-based experiment, run that later as a separate, explicitly isolated task.
- Let the user inspect the agent's own task/report view when available, and paste the final verdict verbatim. Do not paraphrase it.
- Check the shape before relaying: the report must have a "What I did NOT verify" section naming a command and a scope, and must state which depth ran. If the verdict heading carries "Criteria not loaded", fix the path and re-run instead of treating it as a conclusion. Missing any of these, send it back rather than filling it in yourself.
- Re-check load-bearing accusations before acting. If the verdict is clean, stop.
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.
- 12d ago First seen · 15 lines · 49 tokens per session scan A d6cf3ba09701
independent-critic is a skill published in the GitHub repository xinshixu7170/independent-critic (2 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 346 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
shipproof
Evidence-driven acceptance review for AI-generated or human-written software changes. Use when evaluating whether a pull request, diff, repository, API, database migration, frontend change, desktop/kiosk app, or infrastructure change is safe to merge, adopt, or deploy to production. Adapts review scope to detected…
grok-build-delegate
Use the local Grok Build CLI for second-opinion reviews, adversarial critiques, or delegated read-only investigation from Codex.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…