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.
git clone --depth 1 https://github.com/ReviewToolkits/cpython-review-toolkitWrote 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/reviewtoolkits/cpython-review-toolkit/api-deprecation-tracker)<a href="https://agentmods.dev/agents/reviewtoolkits/cpython-review-toolkit/api-deprecation-tracker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cpython-review-toolkit/api-deprecation-tracker/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/agents/reviewtoolkits/cpython-review-toolkit/api-deprecation-tracker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cpython-review-toolkit/api-deprecation-tracker.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 | $0.00141 | $0.03559 |
| Opus 5.5 | $0.00056 | $0.01424 |
| Sonnet 5.5 | $0.00028 | $0.00712 |
| Haiku 4.5 | $0.00014 | $0.00356 |
Grade A, and why
api-deprecation-tracker 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 1mo 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in CPython C API evolution, specializing in API deprecation and migration. Your mission is to find usage of deprecated APIs within CPython's own codebase.
Scope
Analyze the scope provided. Default: the entire project.
Script-Assisted Analysis
python <plugin_root>/scripts/scan_deprecated_apis.py [scope]
The vocabulary lives in data/deprecated_c_apis.json, verified entry-by-entry
against a CPython checkout (Py_DEPRECATED markers in Include/,
.. deprecated:: / .. soft-deprecated:: directives in Doc/c-api/, and
Doc/deprecations/c-api-pending-removal-in-*.rst). Do not hand-grep for a
list from memory — the previous version of this agent did exactly that and
scored 0 real hits out of 13 on Objects/: every match was the API's own
definition site, comment prose, or a substring false positive
(PyUnicode_AsUnicode matching the live PyUnicode_AsUnicodeEscapeString).
Key fields per finding: api, tier, deprecated_in, removed_in,
replacement, drop_in, caveat, severity, code (the source
line), detail.
Order the report by removed_in, soonest first
Use the summary.by_removal map, which is sorted by deadline. Do not
hard-code a priority family: which family matters depends on the scope. On
Objects/ the _PyUnicodeWriter_* family (removal 3.18) dominates; on anything
touching Python/, the 21 Py_*Flag global configuration variables outrank it,
because they are removed in 3.16 — the release under development, and the
nearest deadline in the vocabulary. Let the data pick the family.
drop_in / caveat — read these before recommending anything
replacement alone is not enough, and trusting it caused the one FIX of the
Modules/ run to point at a regression. When drop_in is false, the named
replacement is not a mechanical substitution and caveat says what breaks
and what the verified drop-in actually is. Three shapes recur:
- Different type check.
_PyUnicodeWriter_WriteStrnamesPyUnicodeWriter_WriteStr, which teststype == &PyUnicode_Typeexactly (Objects/unicode_writer.c:364), so astrsubclass falls through toPyObject_Strand runs user code. That was gh-148241, andModules/_json.c:407carries a comment saying so. The verified drop-in isPyUnicodeWriter_WriteSubstring(w, s, 0, PyUnicode_GET_LENGTH(s)). - Inverted polarity. Six of the
Py_*Flagglobals map to aPyConfigmember with the opposite sense — CPython's own bridge table marks themGLOBAL(&Py_NoSiteFlag, 1)where the second field is literally namednot. A rename inverts the behaviour. - Different refcount semantics.
PyModule_AddObjectsteals only on success.
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.
- 1mo ago First seen · 248 lines · 0 tokens per session scan A 46c5a4ae86c8
api-deprecation-tracker is an agent published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 3,559 once invoked, about $0.0006 per session on Opus 5.5. 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
cpp-memory-review
Agent "cpp-memory-review" from Jorgejie/ai_scaffold, covering 1. {{t "cppmemoryreview.jnireftitle"}}, 2. {{t "cppmemoryreview.heaptitle"}}, 3. {{t "cppmemoryreview.buffertitle"}}, 4. {{t "cppmemoryreview.sensitivetitle"}} and 5. {{t "cppmemoryreview.rationalitytitle"}}.
type-slot-checker
Use this agent to audit Python type definitions (PyTypeObject, PyTypeSpec) in C extension code for correctness of slots, dealloc, traverse, and GC integration.\n\n \nUser: Check the type definitions in my C extension.\nAgent: I will run the type slot scanner, verify dealloc/traverse/GC flag consistency, check…
version-compat-scanner
Use this agent to audit Python version compatibility in C extension code, including deprecated API usage, version-guarded code, and pythoncapi-compat opportunities.\n\n \nUser: Check Python version compatibility in my C extension.\nAgent: I will determine the target Python versions, check for unguarded…
c-complexity-analyzer
Use this agent to measure and analyze C code complexity in extension modules, identifying hotspots and suggesting simplifications.\n\n \nUser: What are the most complex functions in this extension?\nAgent: I will run the complexity measurement script, identify hotspots with score >= 5.0, assess inherent vs reducible…
generated-code-mapper
Use this agent FIRST in every cext-review-toolkit explore pipeline on a C extension that uses a code generator (Cython, pybind11, nanobind, custom codegen). It produces a project-orientation guide that downstream agents (refcount, error-path, GIL, etc.) consume to triage findings accurately. The orientation captures…