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/mistakeknot/interdoc/gpt-reviewgit clone --depth 1 https://github.com/mistakeknot/interdocWhat 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 | $0.00302 |
| Opus 5 | $0.00000 | $0.00151 |
| Sonnet 5 | $0.00000 | $0.00060 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
gpt-review 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.
What it actually says
GPT Review Phase
After generation/update, interdoc sends AGENTS.md to Oracle for independent critique.
How It Works
- Pre-flight check verifies Oracle session
- Gathers evidence (git changes, commit messages, detected languages)
- Sends AGENTS.md + source files to GPT with critic prompt
- Parses structured JSON suggestions
- Classifies by significance:
- Non-controversial (auto-applied): low severity, additive suggestions
- Significant (user-prompted): high severity, corrections, 3+ suggestions
Oracle Dependencies
- Oracle CLI installed (
npm i -g @steipete/oracle) - Active ChatGPT session (X11 stack: Xvfb on :99, Chrome)
- Environment:
DISPLAY=:99 CHROME_PATH=/usr/local/bin/google-chrome-wrapper
Helper Scripts
hooks/tools/oracle-review.sh— Sends AGENTS.md to GPT for critiquehooks/tools/sanitize-review.sh— Strips code fences, citation artifactshooks/tools/secret-scan.sh— Filters dangerous files before Oracle upload
Troubleshooting
- Oracle session expired: Run
oracle-loginvia NoVNC, complete Cloudflare check - X11 not running: Check
pgrep -f "Xvfb :99", restart if needed - Review skipped: Normal if Oracle unavailable — generation still works
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 · 32 lines · 0 tokens per session scan A c02677673e5f
gpt-review is an agent published in the GitHub repository mistakeknot/interdoc (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 302 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 2026-08-31.
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.