A set of rules for safe coding and Git work, including secret handling, security checks, pull-request practices, and focused development workflows.

Use it when writing code, changing dependencies, handling secrets, committing, pushing, or reviewing pull requests.

It reduces the chance of committing credentials, damaging shared Git history, skipping useful checks, or mixing unrelated work together.

dev-rules — Skill for Claude Code by Sagargupta16/claude-skills

Install

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.

Any agent

npx skills add Sagargupta16/claude-skills --skill dev-rules

Clone the repo

git clone --depth 1 https://github.com/Sagargupta16/claude-skills

Made for: Claude Code.

Or install dev-rules, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 1 hook.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sagargupta16/claude-skills/dev-rules/github.svg)](https://agentmods.dev/skills/sagargupta16/claude-skills/dev-rules)

Your own site

<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/dev-rules"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/dev-rules/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/dev-rules"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/dev-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,079 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00052	$0.01079
Opus 5.5	$0.00021	$0.00432
Sonnet 5.5	$0.00010	$0.00216
Haiku 4.5	$0.00005	$0.00108

Measured 2mo ago against content hash 8ac3beaa4d30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-rules 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.

plugins/dev-rules/skills/dev-rules/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Development Rules and Guardrails

Git Safety

Rule	Why
Never force push to main/master	Destroys team history, breaks CI
Never `git reset --hard` without confirmation	Irreversible data loss
Never amend published commits	Creates divergent history for collaborators
Never skip pre-commit hooks (`--no-verify`)	Hooks catch real issues
Stage specific files by name	`git add .` risks committing secrets or binaries
Never commit .env, credentials, API keys	Secrets in git history are permanent
Verify current branch before pushing	Avoid pushing to wrong branch

Security

Secrets and Credentials

Never commit .env files, API keys, tokens, passwords, or connection strings
Always use .env.example with placeholder values, never real credentials
If real credentials are found in git history, flag immediately - they must be rotated
Add secret config files to .gitignore (e.g., config/secrets.yml)

Code Security

Validate all user input at system boundaries (API endpoints, form submissions)
Use parameterized queries - never string concatenation for database queries
Sanitize data before rendering in templates (prevent XSS)
Use bcrypt or argon2 for password hashing, never MD5 or SHA for passwords
Set CORS origins from environment variables, never wildcard in production

Dependency Security

Check for known vulnerabilities before adding new packages
Prefer well-maintained packages with active security response
Pin dependency versions in lock files

PR Workflow

When working with pull requests:

Always read comments first before making changes
- gh api repos/{owner}/{repo}/issues/{num}/comments
- gh api repos/{owner}/{repo}/pulls/{num}/comments
Check merge readiness before acting
- gh api repos/{owner}/{repo}/pulls/{num} --jq '{mergeable, mergeable_state, draft}'
Check how far behind the base branch
- gh api repos/{owner}/{repo}/compare/{base}...{head} --jq '{behind_by, ahead_by}'
After fixing/rebasing your own repo's PR - comment a summary of what was done. On upstream or fork PRs, never comment without the user's or maintainer's explicit go-ahead
Before deleting a fork - verify zero open PRs from that fork
When rebasing - squash into clean commits, match project's commit style
Never force-push to someone else's branch - only to your own fork branches

Read the full file on GitHub · 100 lines

Changes

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 · 100 lines · 52 tokens per session scan A 8ac3beaa4d30

Subscribe to this mod's changes

dev-rules is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 1,079 once invoked, about $0.0002 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.

Claude Code Git and workflow Security ai-agents claude developer-tools marketplace plugins

dev-rules next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dev-rulesSagargupta16/claude-skills	Skill	5	yesterday	MIT	A	52	Claude Code
changelog-summarizingshopwareLabs/ai-coding-tools	Skill	45	2d ago	MIT	A	106	Claude Code
plugin-updatingshopwareLabs/ai-coding-tools	Skill	45	2d ago	MIT	A	102	Claude Code
commit-message-writingshopwareLabs/ai-coding-tools	Skill	45	2d ago	MIT	A	160	Claude Code
morning-briefmelodic-software/claude-code-plugins	Skill	30	today	MIT	A	152	Claude Code
realign-file-namesmelodic-software/claude-code-plugins	Skill	30	today	MIT	A	114	Claude Code
applymelodic-software/claude-code-plugins	Skill	30	today	MIT	A	109	Claude Code

dev-rules

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Development Rules and Guardrails

Git Safety

Security

Secrets and Credentials

Code Security

Dependency Security

PR Workflow

What this file has done since we first saw it

dev-rules compared with skills from other repositories