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 agentmods add agents/jscraik/ralph-gold/02-development-workflowgit clone --depth 1 https://github.com/jscraik/ralph-goldWrote 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/jscraik/ralph-gold/02-development-workflow)<a href="https://agentmods.dev/agents/jscraik/ralph-gold/02-development-workflow"><img src="https://agentmods.dev/badge/agents/jscraik/ralph-gold/02-development-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 | $0.00000 | $0.00333 |
| Opus 5 | $0.00000 | $0.00167 |
| Sonnet 5 | $0.00000 | $0.00067 |
| Haiku 4.5 | $0.00000 | $0.00033 |
Grade A, and why
02-development-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 3d 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.
What it actually says
Development workflow
Project structure
- Core code:
/Users/jamiecraik/dev/ralph-gold/src/ralph_gold/ - Tests:
/Users/jamiecraik/dev/ralph-gold/tests/ - Docs:
/Users/jamiecraik/dev/ralph-gold/docs/ - VS Code bridge extension:
/Users/jamiecraik/dev/ralph-gold/vscode/ralph-bridge/ - Install helpers:
/Users/jamiecraik/dev/ralph-gold/scripts/
Build, test, and dev commands
uv syncuv run pytest -quv run python -m ralph_gold.cli --helpuv tool install -e .
Coding style
- Keep Python code under
src/ralph_gold/. - Prefer small single-purpose functions with clear error handling.
- Use
snake_casefor functions and variables;PascalCasefor classes. - Follow adjacent module patterns before adding new abstractions.
- Avoid new dependencies without approval.
Testing guidelines
- Use
pytestundertests/. - Name tests
test_*.py. - Keep fixtures local to each test file unless sharing is required.
- Run
uv run pytest -qbefore opening a PR.
Commit and PR guidance
- Commit message convention: not observed.
- Keep commit messages clear and scoped.
- PRs should include a short summary, test results, and doc updates for behavior 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.
- 3d ago First seen · 37 lines · 0 tokens per session scan A b0f808cb0bb0
02-development-workflow is an agent published in the GitHub repository jscraik/ralph-gold (2 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 333 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 2026-08-31.
Other agents, from other repositories
devops-engineer
You are a DevOps and CI/CD specialist for the Shipwright project. You work on GitHub Actions workflows, deployment pipelines, infrastructure automation, and operational tooling.
shell-script-specialist
You are a shell script development specialist for the Shipwright project — an autonomous delivery platform built entirely in Bash (37+ scripts, 25,000+ lines).
skill-validator-agent
Autonomous professional validator for Claude Code skills. Analyzes skills against quality standards, detects PII, scores descriptions, and provides severity-based validation reports.
critic-munger
Company contrarian thinking advisor (Charlie Munger mental model). Use when questioning the viability of new ideas, identifying fatal flaws in plans, preventing groupthink, conducting inverse reasoning, performing pre-mortem analyses. Must be consulted before any major decision.
sales-ross
Sales Director (Aaron Ross mental model). Use when designing pricing strategy, choosing sales models, conversion rate optimization, customer acquisition cost analysis.
fullstack-dhh
Full-stack tech lead (DHH mental model). Use when writing code and implementing features, choosing technical implementation approaches, code review and refactoring, development tools and process optimization.