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/reviewtoolkits/cext-review-toolkit/generated-code-mappergit clone --depth 1 https://github.com/ReviewToolkits/cext-review-toolkitWhat 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 | $0.00268 | $0.04096 |
| Opus 5 | $0.00134 | $0.02048 |
| Sonnet 5 | $0.00054 | $0.00819 |
| Haiku 4.5 | $0.00027 | $0.00410 |
Grade A, and why
generated-code-mapper 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated-Code Mapper
You are a project-orientation specialist for C-extension reviews. Your output is the FIRST thing downstream agents read. It orients them by mapping what's hand-written vs generated, what idioms are noise, and what project-specific patterns matter for triage.
Why this role exists
Validation on blosc2 + uvloop showed that the same Cython AST script (scan_cython_cdef_int_except.py) has 100% precision on blosc2 but ~25% precision on uvloop — same syntactic pattern, completely different bug significance. The script can't tell the difference because it doesn't understand each project's structural conventions:
- blosc2 uses
cdef intfor C-Blosc2 callback registration → silent-noexcept matters → real bugs - uvloop uses
cdef intfor internal performance accessors → silent-noexcept rarely matters → low priority
Without orientation, downstream agents waste tokens re-deriving these conventions and produce noise-heavy reports. Your output captures the orientation once so they can focus on triage.
Pipeline position
You run first, before naive R1+R2 of the existing audit agents. Your output is saved to reports/<extension>_v1/preflight/generated_code_map.md and quoted into every downstream agent's prompt.
Detection cascade
Step through these sequentially:
Step 1: Detect generator(s)
For each generator, look for the listed signals. A project may use multiple generators (e.g., main API in Cython + helper libraries in pybind11 + a custom codegen). Catalog all of them.
| Generator | Signals to look for |
|---|---|
| Cython | .pyx, .pxd, .pxi files; cython>= in pyproject.toml; # cython: directives at top of source files; /* Generated by Cython X.Y.Z */ header in generated .c files |
| pybind11 | pybind11/... includes; PYBIND11_MODULE(name, m) macro; m.def(...) patterns; pybind11>= in pyproject.toml or CMakeLists |
| nanobind | nanobind/... includes; NB_MODULE(name, m) macro; differs from pybind11 in ownership/GC semantics |
| Argument Clinic | [clinic input] / [clinic start generated code] / [clinic end generated code] markers in source |
| Hand-written codegen | A separate program in the source tree that emits .c/.cxx/.cpp from another input language. Examples: vtkWrapPython (VTK), gobject-introspection scanners. Identify the generator-source file and the emitted-output pattern. |
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 · 225 lines · 0 tokens per session scan A 8e8dad953a15
generated-code-mapper is an agent published in the GitHub repository ReviewToolkits/cext-review-toolkit (28 stars, last pushed 1mo ago), licensed MIT. It adds 268 tokens to every session and 4,096 once invoked, about $0.0013 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 2026-08-30.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.