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 skills add rossumai/claude-marketplace --skill coding-best-practicesgit clone --depth 1 https://github.com/rossumai/claude-marketplaceWrote 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/skills/rossumai/claude-marketplace/coding-best-practices)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/coding-best-practices"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/coding-best-practices/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/skills/rossumai/claude-marketplace/coding-best-practices"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/coding-best-practices.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 | $0.00033 | $0.03763 |
| Opus 5 | $0.00016 | $0.01881 |
| Sonnet 5 | $0.00007 | $0.00753 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade A, and why
coding-best-practices scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Every `requests.get/post/patch/...` must be followed immediately by `.raise_for_status()` before calling `.json()` or accessing `.content`. How it starts
The opening of the file, as written. The whole thing — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding Best Practices — Rossum Serverless Functions
Overview
Audit custom Python hook code against Rossum-specific and general best practices. Rossum serverless functions run as stateless, event-driven Python 3.12 compute (AWS Lambda style). Issues here cause silent failures, data corruption, or security incidents.
Step 1: Find Custom Hook Files
In a prd project, hook .py files live alongside their .json counterparts in <org>/<env>/hooks/. Only hooks that have a .py file contain custom code — the rest are no-code Rossum extensions.
find . -name "*.py" -path "*/hooks/*"
Step 2: Evaluate Each Hook
Work through every checklist item. Flag violations in the output format at the end.
2.1 — Consider Whether Custom Code Is Needed
Before reviewing code quality, ask: could this hook be replaced by a no-code alternative?
- Rossum Store — pre-built extensions (MDH matching, export pipelines, SFI)
- Formula Fields — simple field transformations and calculations
- Export Pipeline — routing, filtering, payload construction
Flag hooks where the entire logic could be replaced by a no-code extension.
2.2 — Security (Critical)
No hardcoded credentials
Passwords, API keys, client secrets must never appear in code. Use payload["secrets"] and define secrets_schema in the hook JSON (outside a prd2 tree, set it via the rossum_create_hook / rossum_patch_hook MCP tools — key names only, a human enters the values):
// hook.json — secrets_schema
{
"type": "object",
"properties": {
"username": { "type": "string", "minLength": 1, "description": "Service account login" },
"password": { "type": "string", "minLength": 1, "description": "Service account password" }
},
"additionalProperties": false
}
The API enforces this shape: top-level keys other than type/properties/additionalProperties are rejected (no $schema, no required), every declared property must be type string, and additionalProperties must be present — HTTP 400 otherwise. Use false (as above) for a fixed credential set; for hooks whose code writes its own secrets at runtime (e.g. OAuth token caches), use "additionalProperties": {"type": "string"} instead, since a closed schema would reject those writes.
# Bad
auth=("api_user", "Hardcoded123")
# Good
auth=(payload["secrets"]["username"], payload["secrets"]["password"])
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.
- 10d ago First seen · 401 lines · 33 tokens per session scan A aca33b4acc2e
coding-best-practices is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 3,763 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.