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 skills/rtazima/claude-proj-blueprint/source-driven-developmentnpx skills add rtazima/claude-proj-blueprint --skill source-driven-developmentgit clone --depth 1 https://github.com/rtazima/claude-proj-blueprintWrote 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/rtazima/claude-proj-blueprint/source-driven-development)<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/source-driven-development"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/source-driven-development.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 | $0.00078 | $0.00943 |
| Opus 5 | $0.00039 | $0.00472 |
| Sonnet 5 | $0.00016 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
source-driven-development 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source-Driven Development
Every framework-specific decision must be backed by official documentation, not training data. LLMs hallucinate APIs, invent method signatures, and confuse library versions. The antidote is to verify against the source of truth before writing code.
Rules
- Detect the stack first — read
CLAUDE.md,package.json,requirements.txt,go.mod, or equivalent to know exact versions - Fetch docs, don't guess — use
WebFetchto read official docs for the specific version in use - Cite your source — add a comment or docstring with the doc URL when using a non-obvious API
- Say UNVERIFIED — if you cannot find official documentation for a claim, explicitly mark it as
// UNVERIFIED: could not find docs for this API - Never cite Stack Overflow, blog posts, or tutorials as primary source — they may be outdated or wrong. Official docs and source code are the only primary sources
- Version matters — docs for v3 don't apply to v2. Always check the version installed
Workflow
Phase 1: Detect stack and versions
# Node.js
cat package.json | grep -A1 '"dependencies"'
# Python
cat requirements.txt # or pyproject.toml
# Go
cat go.mod
Phase 2: Before implementing
For each framework-specific decision:
- Identify the specific API/method/pattern you need
- Fetch the official docs page for that API
- Verify: does this method exist? What are the parameters? What version introduced it?
- If docs are unavailable → mark as UNVERIFIED and note what you assumed
Phase 3: Implement with citation
// Ref: https://docs.example.com/api/v3/client#create
const client = new Client({ timeout: 5000 });
Phase 4: Verify after implementing
- Does the code compile/type-check? (catches hallucinated APIs)
- Do tests pass? (catches wrong method signatures)
- Are all UNVERIFIED markers resolved or documented?
Source hierarchy
| Priority | Source | Use for |
|---|---|---|
| 1 | Official docs (versioned) | API signatures, configuration, behavior |
| 2 | Source code (GitHub) | When docs are incomplete or ambiguous |
| 3 | Official migration guides | Version upgrade patterns |
| 4 | Official examples/cookbooks | Integration patterns |
| 5 | UNVERIFIED (mark explicitly) | Last resort — document the assumption |
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.
- 4d ago First seen · 85 lines · 78 tokens per session scan A 10ae5161ed94
source-driven-development is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 943 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
modular-skills
Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.
product-image-processor
Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.
tool-catalog
Show the available Architecture Studio skills and their host-appropriate commands, plus Claude Code's native Architecture Studio agents. Use when the user invokes tool-catalog, asks "what can you do" or "what skills are available", or wants a directory of plugin commands. Do not use for a host's native skill-list…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.