source-driven-development

A development workflow that checks official documentation and version-specific guidance before making framework or library decisions.

In plain words
What is it for?
Use it when implementing or reviewing framework-specific code that needs current, source-backed guidance.
Why use it?
It reduces mistakes caused by relying on outdated knowledge, especially when APIs, recommended patterns, or migrations have changed.

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/threat-vector-security/guardian-agent/source-driven-development
Any agent
npx skills add Threat-Vector-Security/guardian-agent --skill source-driven-development
Clone the repo
git clone --depth 1 https://github.com/Threat-Vector-Security/guardian-agent

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 852 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 $0.00034 $0.00852
Opus 5 $0.00017 $0.00426
Sonnet 5 $0.00007 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 2d ago against content hash b087f8ac6bb6, 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 2d 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.

skills/source-driven-development/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Source-Driven Development

Overview / When to Use

Ground framework-specific decisions in authoritative sources. Do not rely on model memory for APIs, recommended patterns, deprecations, or migration guidance when the code depends on a specific library or version.

Use this when:

  • a request depends on the current best practice for a framework or library
  • the user asks for official docs, current guidance, citations, or a documented pattern
  • you are writing boilerplate or patterns likely to be copied elsewhere
  • the repo version matters for the correctness of the implementation

Do not use this for pure logic, file moves, naming changes, or other work that is stable across versions.

Process

  1. Detect the stack and exact version from the repo before making framework-specific claims.
    • Read package.json, pyproject.toml, Cargo.toml, go.mod, or the equivalent dependency source.
    • State the version you found when it affects the answer.
  2. Fetch the narrow official source for the exact feature or API.
    • Prefer official docs, official migration guides, official changelogs, MDN, or runtime compatibility sources.
    • Fetch the specific page for the feature, not the whole documentation site.
  3. Compare the docs with the current repo conventions before editing.
    • If the docs and the codebase disagree, surface the conflict instead of silently choosing one.
    • If the version is ambiguous, stop and clarify before writing the pattern.
  4. Implement only what you can verify.
    • Follow the documented API shape and recommended pattern.
    • If the docs do not support the pattern, label it UNVERIFIED instead of guessing.
  5. Cite the source for non-obvious framework decisions.
    • Include the exact URL in the response.
    • Prefer deep links or anchors when available.
  6. Verify the real proof surface after the change.
    • Run the strongest relevant repo checks, not just the smallest local assertion.

Common Rationalizations

Rationalization Reality
"I know this API already." Framework memory goes stale. One signature or lifecycle change is enough to make the implementation wrong.
"Docs lookup is overkill for a small change." Small framework mistakes become copy-paste templates. They are cheap to prevent and expensive to unwind later.
"I'll just hedge and say it might be outdated." Hedging is not verification. Either cite the official source or mark the pattern unverified.
"The repo already does it this way, so I'll follow that." Existing code can be outdated. Compare the repo pattern with the current official guidance before reinforcing it.

Read the full file on GitHub · 74 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 74 lines · 34 tokens per session scan A b087f8ac6bb6

Subscribe to this mod's changes

source-driven-development is a skill published in the GitHub repository Threat-Vector-Security/guardian-agent (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 852 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

orloj-generator

Interactive scaffold generator for Orloj multi-agent systems. Use this skill whenever someone wants to create, set up, scaffold, bootstrap, or generate an Orloj agent system, pipeline, swarm, or hierarchy. Also trigger when users mention "orlojctl init", ask how to get started with Orloj, want to build a multi-agent…

OrlojHQ/orloj · 168 tokens

agentfootprint

Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.

footprintjs/agentfootprint · 72 tokens

billing

Use for refunds, disputed charges, invoices and any billing question.

footprintjs/agentfootprint · 15 tokens

shipping

Use for delivery estimates, lost parcels and address changes.

footprintjs/agentfootprint · 13 tokens

agentfootprint

Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.

footprintjs/agentfootprint · 72 tokens

titanclip

Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…

CES-Ltd/TitanClip · 87 tokens