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 agentmods add skills/clay-good/openlore/openlore-orientnpx skills add clay-good/OpenLore --skill openlore-orientgit clone --depth 1 https://github.com/clay-good/OpenLoreWrote 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/clay-good/openlore/openlore-orient)<a href="https://agentmods.dev/skills/clay-good/openlore/openlore-orient"><img src="https://agentmods.dev/badge/skills/clay-good/openlore/openlore-orient.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.01500 |
| Opus 5 | $0.00020 | $0.00750 |
| Sonnet 5 | $0.00008 | $0.00300 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
openlore-orient 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 5d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLore — orient before you read
This project uses OpenLore to maintain a deterministic, graph-native model of the codebase: every function, every caller, every spec section, every file. The orient tool collapses what would otherwise be a chain of analyze_codebase → search_code → search_specs → suggest_insertion_points into a single call.
The single most important habit when working in this repo: call orient before opening source files for any non-trivial task.
When to use this skill
Call orient at the start of any of these:
- New task in the repo — even ones that feel small. The graph knows things the file tree doesn't.
- Unknown function or symbol — instead of grepping blind, ask
orientand let it return the function, its callers, and the spec section that owns it. - Planning a cross-module change —
orientreturns insertion points ranked by structural fit, so you start at the right boundary instead of the most-recently-viewed file. - After an Epistemic Lease prefix appears — when a tool response says you're stale, re-orient before continuing. Acting on stale context is the most common failure mode.
If you are reading source files without having called orient first, you are probably wasting tokens.
How to use it
Preferred: via the OpenLore MCP server
If openlore is registered as an MCP server in this project (look for .mcp.json → mcpServers.openlore — the project-scope file Claude Code reads; not .claude/settings.json, which it ignores for MCP), call the orient tool directly through the MCP interface. This is the lowest-latency path and gives the model access to whatever tool surface the server was wired with — the lean 10-tool navigation preset by default (openlore install --preset full wires all 62), not just orient.
Fallback: via the shell wrapper
bash scripts/orient.sh "<task description>"
(On Windows: powershell -File scripts/orient.ps1 "<task description>")
The wrapper tries the direct CLI subcommand first (npx --yes openlore orient --json --task "<task>") and falls back to driving the openlore mcp server over stdio JSON-RPC via the sibling orient-via-mcp.mjs helper on older openlore versions that predate the CLI subcommand. Either path produces real orient JSON on stdout. Parse these arrays from the result:
What ships with it
6 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.
- 5d ago First seen · 73 lines · 40 tokens per session scan A 607b57eada47
openlore-orient is a skill published in the GitHub repository clay-good/OpenLore (296 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,500 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.
Other skills, from other repositories
campus-fyp-architecture
Activate when a student asks for help architecting, scoping, or documenting a university Final Year Project (FYP), software capstone, or research-linked undergraduate thesis project — trigger phrasings include "help me design the architecture for my final year project", "what tech stack should I use for my FYP", "how…
architecture-decision-record-creator
Create structured Architecture Decision Records (ADRs) with 7 sections to document architecture decisions with full justification. Use this skill whenever the user has made or needs to make an architecture decision, wants to document why a technical choice was made, is choosing between technologies or patterns, needs…
software-architect
Software architecture engineering consultancy skill. Analyzes overall application structure, recommends sustainable approaches, enforces architectural consistency, and documents decisions for future sessions. Use this skill whenever the user asks about system design, architecture decisions, feature integration…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.