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 tranhieutt/software_development_department --skill source-driven-developmentgit clone --depth 1 https://github.com/tranhieutt/software_development_departmentWrote 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/tranhieutt/software_development_department/source-driven-development)<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.
<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>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 | $0.00045 | $0.01486 |
| Opus 5 | $0.00023 | $0.00743 |
| Sonnet 5 | $0.00009 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00149 |
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.
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 |
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.
- 9d ago First seen · 189 lines · 45 tokens per session scan A 5e1093b91e0b
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.
Other skills, from other repositories
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
flutter-ui
Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
database-migrations
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
scan
Scan project once per session. Run first — all other skills depend on this.
tdd
Strict test-driven development for behavior changes. Requires verified RED before production code, minimal GREEN, and refactor only after passing tests.