source-driven-development

A coding workflow that checks official documentation before using a framework, library, or unfamiliar programming interface. It records what was verified and points out anything that could not be confirmed.

In plain words
What is it for?
Use it when building with external libraries or frameworks, choosing an unfamiliar API, or introducing a pattern that is not already established in the codebase.
Why use it?
It reduces outdated, deprecated, or invented code caused by relying on memory or incomplete examples.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/jmxt3/gitscape.ai/source-driven-development
Any agent
npx skills add jmxt3/gitscape.ai --skill source-driven-development
Clone the repo
git clone --depth 1 https://github.com/jmxt3/gitscape.ai

Made for: Claude Code, Codex.

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,093 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00040 $0.01093
Opus 5 $0.00020 $0.00547
Sonnet 5 $0.00008 $0.00219
Haiku 4.5 $0.00004 $0.00109

Measured 3d ago against content hash 62f93c4c09ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.agents/skills/source-driven-development/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source-Driven Development

Overview

Every framework decision and library usage should be grounded in official documentation. AI agents have training cutoffs and can produce outdated, deprecated, or hallucinated API patterns. Source-driven development means: verify before you code, cite what you verified, and flag what you couldn't confirm.

When to Use

  • Using any external library or framework
  • Implementing a pattern that isn't already established in the codebase
  • Unsure whether an API or approach is current
  • Seeing a pattern that looks right but isn't confirmed in the existing codebase

The Process

Step 1: Identify What Needs Verification

Before writing any code that uses an external library:

  1. List the specific APIs, functions, or patterns you plan to use
  2. Note the version you're targeting (check requirements.txt, package.json, or pyproject.toml)
  3. Flag anything you're not 100% confident is current

Step 2: Verify in Official Sources

Priority order for sources:

  1. Official docs — the library's own documentation site
  2. Official GitHub — the library's README.md, CHANGELOG.md, or examples/
  3. Release notes — for the specific version in use
  4. Existing codebase — how the library is already used in this project

Never use as authoritative sources:

  • Stack Overflow answers (can be outdated)
  • Blog posts (may target a different version)
  • Your own training knowledge without verification
  • ChatGPT or other AI outputs as a source of truth

Step 3: Cite Your Sources

When writing code that uses verified patterns, leave a reference comment for future maintainers:

# FastAPI dependency injection pattern
# Source: https://fastapi.tiangolo.com/tutorial/dependencies/
async def get_db() -> AsyncGenerator[AsyncSession, None]:
    async with AsyncSessionLocal() as session:
        yield session
// React Query v5 data fetching
// Source: https://tanstack.com/query/v5/docs/framework/react/guides/queries
const { data, isLoading } = useQuery({
  queryKey: ['skills', repoId],
  queryFn: () => fetchSkills(repoId),
});

Read the full file on GitHub · 124 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.

  1. 3d ago First seen · 124 lines · 40 tokens per session scan A 62f93c4c09ed

Subscribe to this mod's changes

source-driven-development is a skill published in the GitHub repository jmxt3/gitscape.ai (33 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,093 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 2026-08-30.

Related

Other skills, from other repositories