Borrowing it
Nothing to install: this file belongs to strands-rl/strands-sglang. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/strands-rl/strands-sglang/main/.claude/commands/audit-docstrings.mdgit clone --depth 1 https://github.com/strands-rl/strands-sglangWrote 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/commands/strands-rl/strands-sglang/audit-docstrings)<a href="https://agentmods.dev/commands/strands-rl/strands-sglang/audit-docstrings"><img src="https://agentmods.dev/badge/commands/strands-rl/strands-sglang/audit-docstrings/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/commands/strands-rl/strands-sglang/audit-docstrings"><img src="https://agentmods.dev/badge/commands/strands-rl/strands-sglang/audit-docstrings.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 | $0.00000 | $0.01029 |
| Opus 5.5 | $0.00000 | $0.00412 |
| Sonnet 5.5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
audit-docstrings 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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit a package's docstrings and comments against the style rules in AGENTS.md, and fix what fails.
Target is $ARGUMENTS — a package or file path under src/strands_sglang/ (e.g. eval,
environments/harbor, sglang.py). If not provided, ask which one; never audit
everything at once.
Read the files. Do not grep for candidates.
A script cannot tell a # ---- Task ---- section divider from an explanatory comment, or
judge whether a private helper names a domain concept. Open each file in the target and
read it. Counting tools are for reporting scale, not for deciding.
The decisions, in the order they resolve
1. Args: is all-or-nothing. D417 rejects a partial section, so the question is
never "does this parameter need a line" but "do this function's parameters need
explaining at all". Default no.
Delete the whole section when every line restates its annotation:
client: SGLangClient # signature
client: `SGLangClient` for HTTP communication with the server. # the same fact
Keep it when a parameter's meaning isn't in its type: resolution order, ownership, what
None falls back to, units, what happens when two arguments disagree, or a name that
implies less than it does (env_hook_path: str is really a dotted path to a callable
returning an AsyncEnvFactory).
2. Returns:/Yields: earn their place against the annotation.
-> tuple[list[ToolResultContent], Literal["success", "error"]] needs no "a tuple of
(content, status)". A -> str that is really a JSON envelope does. The poorer the type,
the more the section is worth.
3. Notes: is a footnote; the body is the explanation. Delete the sentence and see
what breaks. If the function stops making sense it was body text — why this method
exists, which of two paths to take, what an empty return means. If all that's lost is a
warning, it stays a footnote: thread-safety, a teardown contract, an upstream quirk, a
deliberate divergence from a reference implementation.
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.
- 2mo ago First seen · 88 lines · 0 tokens per session scan A 491a3d0f3e03
audit-docstrings is a command published in the GitHub repository strands-rl/strands-sglang (79 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,029 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 2026-08-30.
Other commands, from other repositories
refactor
Systematic code refactoring with smart scope detection.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
spec-trace-requirements
You are verifying that implementation changes trace back to specification requirements.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
boot
Start a new PromptKit prompt assembly session (alias for /bootstrap).