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 humanerd-drew/opencode-drewgent --skill vault-naming-conventiongit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/vault-naming-convention)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/vault-naming-convention"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/vault-naming-convention/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/humanerd-drew/opencode-drewgent/vault-naming-convention"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/vault-naming-convention.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 | $0.00037 | $0.05334 |
| Opus 5.5 | $0.00015 | $0.02134 |
| Sonnet 5.5 | $0.00007 | $0.01067 |
| Haiku 4.5 | $0.00004 | $0.00533 |
Grade A, and why
vault-naming-convention 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 1mo 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 — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault Naming Convention
Every file in the {{AGENT_NAME}} vault is a node in the knowledge graph. Filename uniqueness ensures wikilinks resolve deterministically. P-layer prefix preserves priority identity. Exclusion boundaries keep operational noise out of the graph.
Why This Matters (The SEO of Knowledge)
Duplicate filenames waste "resolution budget" — the same way duplicate content wastes search engine crawl budget:
[[SOUL]]with 4SOUL.mdfiles → Obsidian guesses, possibly wrong[[SCHEMA]]with 3SCHEMA.mdfiles → ambiguous reference- Agent reading the vault must resolve ambiguity → compute waste
From NeuronFS: the P-layer prefix (P0-P6) is structural IDENTITY, not just a folder. Losing it in a short-name link loses priority information.
Rule: Unique Basenames in Structural Zones
Structural zones = paths that form the knowledge graph:
P0-brainstem/throughP6-prefrontal/skills/(each skill has its ownSKILL.md)YOUR_SITE/
Non-structural zones (excluded from Obsidian, can have duplicates):
source/— {{AGENT_NAME_LOWER}}-agent upstream codecron/output/— operational logs.trash/— recovery staging_agent/— runtime statenode_modules/,archive/
Enforcement
Every .md file in structural zones must have a unique basename (case-sensitive):
find ~/.{{AGENT_NAME_LOWER}} -name '*.md' \
-not -path '*/cron/*' -not -path '*/.trash/*' \
-not -path '*/source/*' -not -path '*/_agent/*' \
-not -path '*/node_modules/*' -not -path '*/archive/*' \
2>/dev/null | while read f; do basename "$f"; done \
| sort | uniq -c | sort -rn | awk '$1 > 1 {print $1, $2}'
Wikilink Convention by Scope
| Scope | Recommended Style | Example |
|---|---|---|
| Unique filename | Short name [[Slug]] |
[[SELF_MODEL]], [[rules]] |
| Non-unique filename | Full path [[P-layer/path/Slug]] |
[[@identity/persona/SOUL]] (not bare [[SOUL]]) |
| Skill file | [[skills/category/name/SKILL]] |
[[skills/devops/kanban-worker/SKILL]] |
| Neuron file | [[@identity/禁/slug]] |
[[@identity/禁/禁task_qa_gate.neuron]] |
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.
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.
- 1mo ago First seen · 490 lines · 37 tokens per session scan A 76214c4e2b9e
vault-naming-convention is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (3 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 5,334 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
chief-of-staff
Personal Chief of Staff system for ADHD-ish operators. Vault-based, loop-driven, nervous-system-aware. Built and lived-in across daily sessions on real consulting, content, and long-running personal work.
constellation-vault
Build the live object graph (Constellation) and export an Obsidian vault with verified wikilinks from a running ProtoOS world.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, list, or version-gated kanban views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
wiki-retrieve
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…
llm-wiki
Explain and apply the foundational LLM Wiki architecture and knowledge-management strategy. Use for setup, architecture, schema, or organization decisions; operational ingest/query/lint work uses dedicated skills.
wiki-lint
Audit wiki health: broken links, orphans, contradictions, stale content, lifecycle and tag issues. Use for maintenance or health checks. Default is report-only; use wiki-dedup for page-identity merges.