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/cpython-review-toolkit/include-graph-mappergit clone --depth 1 https://github.com/ReviewToolkits/cpython-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 | $0.00012 | $0.01996 |
| Opus 5 | $0.00006 | $0.00998 |
| Sonnet 5 | $0.00002 | $0.00399 |
| Haiku 4.5 | $0.00001 | $0.00200 |
Grade A, and why
include-graph-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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert C build systems analyst specializing in include dependency management. Your mission is to map CPython's #include graph and identify structural issues.
Scope
Analyze the scope provided. Default: the entire project.
Script-Assisted Analysis
python <plugin_root>/scripts/analyze_includes.py [scope]
Every directive is resolved against the build include path (<includer's own dir>, Include/, Include/internal/, Include/cpython/, project root) before it is classified or graphed. That matters because CPython includes its internal headers by bare name — #include "pycore_object.h" — so anything keyed on the directive text is wrong on this codebase.
Key fields:
include_graph: file →[{header, kind, resolved, tier}].resolvedis the repo-relative path; empty when the directive names no file in the tree.reverse_graph: resolved header →[files including it]. This answers the actual preflight question, "who depends on me?".fan_in[]: most-included headers, ranked.countis tree-wide;within_scopeis the count restricted to the scan root. Quotecountfor blast radius andwithin_scopeonly when you mean "inside this directory" — forpycore_tuple.hthose are 68 and 20.symbol_fan_in[]: perInclude/**.h,exported_symbols(how many C-API names it publishes) andreferencing_files(how many files tree-wide use one). Emitted in full, not truncated.fan_out[]: files with the most includes, ranked.cycles: circular chains over the resolved graph. Always computed tree-wide, because a header↔header cycle is invisible from a subdirectory scan.api_tiers: headers bucketedpublic/cpython/internal/generated/vendored/other-local/unresolved/system. Scoped to the scan root;summary.api_tiers_tree_widehas the whole-checkout counts.unresolved_directives[]: directives that name no file in the tree — platform-conditional (windows.h), third-party (openssl/*.h,krml/*.h), or build-generated. Roughly 4% of local directives. They are unresolved, not public.
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 · 118 lines · 12 tokens per session scan A a7e8acb31bea
include-graph-mapper is an agent published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,996 once invoked, about $0.0001 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 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.