source-driven-development

source-driven-development is a skill for Claude Code from tranhieutt/software_development_department. It costs 45 tokens per session (1,486 once invoked), scanned A, original, MIT.

A source-checking skill verifies framework, library, API, and platform decisions against their current official documentation.

In plain words
What is it for?
Use it when a technical plan or implementation depends on current APIs, version-specific rules, official recommendations, or compatibility details.
Why use it?
It reduces errors caused by relying on outdated behavior, deprecated features, or incorrect assumptions about external systems.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter.

Good fit Use it when a technical plan or implementation depends on current APIs, version-specific rules, official recommendations, or compatibility details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tranhieutt/software_development_department/source-driven-development
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 tranhieutt/software_development_department --skill source-driven-development
Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department

Made for: Claude Code.

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.

agentmods badge for source-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/tranhieutt/software_development_department/source-driven-development/github.svg)](https://agentmods.dev/skills/tranhieutt/software_development_department/source-driven-development)
Your own site
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/source-driven-development"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/source-driven-development/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.

agentmods 80×15 button for source-driven-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/source-driven-development"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/source-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,486 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.01486
Opus 5 $0.00023 $0.00743
Sonnet 5 $0.00009 $0.00297
Haiku 4.5 $0.00005 $0.00149

Measured 9d ago against content hash 5e1093b91e0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 9d 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.

.claude/skills/source-driven-development/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source-Driven Development

Purpose

source-driven-development verifies technical correctness against authoritative external sources. It prevents agents from implementing framework, library, API, or platform patterns from stale memory.

This skill does not replace spec-driven-development. It verifies the technical decisions inside a spec, plan, or implementation.

spec-driven-development   = what we are building and why
source-driven-development = whether the technical pattern is correct today

When to Use

Use this workflow when any decision depends on external technical truth:

  • Framework or library APIs, especially version-specific behavior.
  • Runtime or platform constraints.
  • Officially recommended patterns for routing, forms, auth, data fetching, state management, migrations, deployment, or testing.
  • Deprecation, migration, or compatibility questions.
  • User asks for "latest", "official", "best practice", "correct", "current", "documented", or "standards-compliant" implementation.
  • A spec proposes a technical pattern that may conflict with current docs.

Do not use this workflow for pure product intent, copy changes, simple local logic, naming cleanup, or code whose correctness does not depend on an external versioned source.

Position in SDD

Use this as a verification layer:

New feature:
spec-driven-development -> source-driven-development if technical docs matter
-> planning-and-task-breakdown -> test-driven-development

Existing spec:
review-spec -> source-driven-development if technical docs matter
-> planning-and-task-breakdown

Implementation/review conflict:
source-driven-development finds docs/spec mismatch -> spec-evolution

If official sources contradict the approved spec, do not silently change the spec or implementation. Route through spec-evolution and ask the user to approve the updated path.

Source Hierarchy

Use the strongest available source for the specific decision:

Priority Source
1 Official framework, library, product, or API documentation
2 Official migration guides, release notes, changelogs, or RFCs
3 Official standards bodies or platform references such as MDN/web.dev
4 Runtime compatibility data from maintained compatibility references

Read the full file on GitHub · 189 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. 9d ago First seen · 189 lines · 45 tokens per session scan A 5e1093b91e0b

Subscribe to this mod's changes

source-driven-development is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,486 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 2026-09-03.