Borrowing it
Nothing to install: this file belongs to flowing-abyss/obsidian-hybrid-search. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/flowing-abyss/obsidian-hybrid-search/master/.ai/skills/source-driven-development/SKILL.mdgit clone --depth 1 https://github.com/flowing-abyss/obsidian-hybrid-searchWrote 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/flowing-abyss/obsidian-hybrid-search/source-driven-development)<a href="https://agentmods.dev/skills/flowing-abyss/obsidian-hybrid-search/source-driven-development"><img src="https://agentmods.dev/badge/skills/flowing-abyss/obsidian-hybrid-search/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/flowing-abyss/obsidian-hybrid-search/source-driven-development"><img src="https://agentmods.dev/badge/skills/flowing-abyss/obsidian-hybrid-search/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 | $0.00052 | $0.01471 |
| Opus 5.5 | $0.00021 | $0.00588 |
| Sonnet 5.5 | $0.00010 | $0.00294 |
| Haiku 4.5 | $0.00005 | $0.00147 |
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 today.
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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source-Driven Development
Overview
Verify unfamiliar, version-sensitive, newly introduced, deprecated, security-sensitive, or compatibility-relevant API decisions against authoritative documentation, rather than implementing them from memory , training data goes stale, APIs get deprecated, best practices evolve. Routine use of an already-established project pattern doesn't need a fresh research pass; see When to Use below for the actual triggers.
For this repository, that includes Node.js, SQLite, MCP, embedding providers, local inference, new dependencies, and platform compatibility.
When to Use
Required when at least one of these is true:
- the API involved is unfamiliar , not something already used correctly elsewhere in this codebase
- correctness depends on the specific version in use (the pattern differs between versions)
- a new dependency is being added
- a library/framework upgrade or version migration is being performed
- the API is deprecated, experimental, or otherwise unstable
- the integration is security-sensitive
- behavior depends on platform/runtime compatibility
- the user explicitly asked for a documented or verified implementation
- the existing code and the official documentation look genuinely incompatible (see Precedence below)
Not required , do not activate for:
- any call to an API already used correctly elsewhere in this codebase
- mechanical edits (renaming, formatting, moving files)
- local refactoring that doesn't change a contract
- code fully determined by an approved plan's
Interfacesblock or an existing type definition , implement to that, don't re-derive it from docs - copying an existing, already-verified pattern from this project
- pure business logic with no framework/library surface
A wish to move fast doesn't cancel this skill on its own , if the change also involves a security-sensitive, deprecated, or compatibility-sensitive API, speed isn't the deciding factor.
Precedence
When official documentation, the approved spec/plan, and existing project code disagree, resolve in this order:
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.
- today First seen · 129 lines · 52 tokens per session scan A 25ded1ac1e91
source-driven-development is a skill published in the GitHub repository flowing-abyss/obsidian-hybrid-search (113 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,471 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-24.
Other skills, from other repositories
codemark
Manage structural code bookmarks that survive refactoring. Use when the user says "remember this", "bookmark this", "save this location", "load my bookmarks", "what do I have bookmarked", "mark this code", "codemark", or when starting a new session and needing to reload context from a previous session. Also use…
qdrant-vector-search
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
notebrain-assistant
Search and explore an Obsidian vault through the NoteBrain CLI (semantic search, tags, backlinks, connections, hidden links, boosted retrieval). Use it whenever the user mentions their notes, knowledge base, Obsidian vault, semantic search, finding connections or unlinked notes, or asks exploratory questions like…
palaia-memory
Check this person's shared memory before answering anything about their own work, and add to it when something is worth keeping. It holds their projects, decisions and reasons, house conventions (naming, commit messages, tests, releases, review and escalation), people and hard-won details, and every AI tool they use…
palaia-messenger
Register this session with the shared directory so other AI sessions and this person's dashboard can see what you are doing, then use it to reach another live session directly instead of relaying everything through the person. Use it at the start of a task, before picking one up, when your work depends on or informs…
palaia-capture
Save what this person tells you into their shared memory, which every AI tool they use can read. Use it the moment they state a decision and the reason for it, a convention, a correction, or a detail that was expensive to work out — including when they mention it in passing on the way to a different question. Save it…