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 Sagargupta16/claude-skills --skill dev-workflowgit clone --depth 1 https://github.com/Sagargupta16/claude-skillsWrote 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/sagargupta16/claude-skills/dev-workflow)<a href="https://agentmods.dev/skills/sagargupta16/claude-skills/dev-workflow"><img src="https://agentmods.dev/badge/skills/sagargupta16/claude-skills/dev-workflow.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 | $0.00042 | $0.00964 |
| Opus 5 | $0.00021 | $0.00482 |
| Sonnet 5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
dev-workflow 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Workflow Patterns
Quick Reference
| Task | Command | What It Does |
|---|---|---|
| Commit | /commit |
Stage changes, write conventional commit message |
| Review | /review |
Analyze branch changes for bugs, security, quality |
| Test | /test |
Detect test framework, run tests, diagnose failures |
| Fix | /fix |
Trace root cause, implement minimal fix, verify |
| PR | /pr |
Create pull request with summary and test plan |
| Status | /status |
Full repo overview: branches, PRs, CI, sync state |
| Check PR | /check-pr |
CI status, reviews, comments, merge readiness |
Commit Workflow
- Run
git statusandgit diffto understand changes - Run
git log --oneline -5to match the repo's commit style - Stage only relevant files (never stage .env, credentials, binaries)
- Write a conventional commit message:
- Format:
type: short description - Types:
feat,fix,refactor,docs,test,chore,style,perf - Focus on WHY, not WHAT
- Keep first line under 72 chars
- Format:
- Never push unless explicitly asked
Code Review Checklist
When reviewing branch changes (git diff main...HEAD):
| Category | Check For |
|---|---|
| Logic | Bugs, off-by-one errors, null handling |
| Security | Injection, XSS, secrets exposure, CORS |
| Performance | N+1 queries, unnecessary loops, missing indexes |
| Error handling | Unhandled exceptions, missing edge cases |
| Style | Consistency with surrounding code |
| Tests | New code covered? Edge cases tested? |
| API | Breaking changes to public interfaces? |
Provide: overall assessment (ship it / needs changes / major issues), specific issues with file:line references, suggested fixes.
Test Runner
Detect the framework and run tests:
| Config File | Framework | Command |
|---|---|---|
package.json (scripts.test) |
npm/yarn/pnpm | npm test / pnpm test |
pytest.ini / pyproject.toml |
pytest | pytest |
Cargo.toml |
cargo | cargo test |
go.mod |
go | go test ./... |
Makefile (test target) |
make | make test |
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 · 100 lines · 42 tokens per session scan A 0d8adb58d998
dev-workflow is a skill published in the GitHub repository Sagargupta16/claude-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 964 once invoked, about $0.0002 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 skills, from other repositories
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-gate
Use before an agent-produced diff is committed, pushed, opened as a PR, merged, landed, or applied to user files when explicit implementation approval is missing. Trigger for review gate, review pack, approve before landing, diff first then land, human approval, merge gate, commit gate, push gate, or PR readiness.…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
commit-message-writing
Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…
address-pr-feedback
Unified PR feedback workflow - collect, triage, and fix review comments in a single command.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.