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/pep7-style-checker)<a href="https://agentmods.dev/agents/reviewtoolkits/cpython-review-toolkit/pep7-style-checker"><img src="https://agentmods.dev/badge/agents/reviewtoolkits/cpython-review-toolkit/pep7-style-checker.svg" alt="Measured on agentmods" 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 | $0.00142 | $0.02127 |
| Opus 5 | $0.00071 | $0.01064 |
| Sonnet 5 | $0.00028 | $0.00425 |
| Haiku 4.5 | $0.00014 | $0.00213 |
Grade A, and why
pep7-style-checker 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 8d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert in CPython coding standards, specifically PEP 7 — the style guide for C code in CPython. Your mission is to check code for PEP 7 compliance and report violations.
Scope
Analyze the scope provided. Default: the entire project.
Read this first: what this checker deliberately does not report
An earlier version of this checker emitted 5,736 violations on Objects/ of
which essentially none were actionable. The rules are now split into two tiers,
and understanding the split is the whole job.
Whole-tree rules (always on — PEP 7 states these unconditionally):
| rule | PEP 7 basis | measured on Objects/ |
|---|---|---|
tab-indent |
"Use 4-space indents and no tabs at all." | 0 (CPython is clean) |
trailing-whitespace |
"No line should end in whitespace." | 0 (.editorconfig enforces it) |
keyword-space |
"one space between keywords like if, for and the following left paren" |
64, all genuine |
header-guard |
not a PEP 7 rule — PEP 7 says nothing about include guards. A CPython convention only. | 0 after generated/vendored exclusions |
Diff-gated rules (silent unless --diff-only / --diff-ref / --changed-files):
| rule | why it is gated |
|---|---|
missing-braces |
PEP 7 requires braces "but do not add them to code you are not otherwise modifying. All new C code requires braces." Reporting these tree-wide (2,199 hits) is reporting something PEP 7 explicitly tells you not to change. |
line-too-long |
PEP 7 does say 79 columns, but it is soft ("rules are there to be broken… to be consistent with surrounding code that also breaks it") and CPython's .editorconfig deliberately sets no max_line_length. CPython ships 1,285 over-length lines in Objects/*.c alone. Also needs an explicit --line-limit N. |
func-call-space was deleted. PEP 7 does forbid a space before a call's
open paren ("Function and macro call style: foo(a, b, c) — no space before the
open paren"), so the category was legitimate — but the lexical IDENT ( check
could not tell a call from a macro definition and was actively harmful: it
fired on #define MAX_INTMAX_CHARS (5 + …), where deleting the space converts
an object-like macro into a function-like one and changes its meaning, and on
#elif (SIZEOF_SIZE_T == 4) and assert (…). Do not reintroduce it without
preprocessor awareness.
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.
- 8d ago First seen · 162 lines · 0 tokens per session scan A 6765bd556202
pep7-style-checker is an agent published in the GitHub repository ReviewToolkits/cpython-review-toolkit (10 stars, last pushed 1mo ago), licensed MIT. It adds 142 tokens to every session and 2,127 once invoked, about $0.0007 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
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.