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/emergent-wisdom/understanding-graph/orientnpx skills add emergent-wisdom/understanding-graph --skill orientgit clone --depth 1 https://github.com/emergent-wisdom/understanding-graphWrote 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/emergent-wisdom/understanding-graph/orient)<a href="https://agentmods.dev/skills/emergent-wisdom/understanding-graph/orient"><img src="https://agentmods.dev/badge/skills/emergent-wisdom/understanding-graph/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 | $0.00045 | $0.00592 |
| Opus 5 | $0.00023 | $0.00296 |
| Sonnet 5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
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 4d 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.
What it actually says
Orient Without a Ritual
Orientation has one purpose: bring forward graph state that could change the next move. Do not dump the graph, perform maintenance, or delay a simple task merely because a graph exists.
- Inspect
project_listwhen no current project is established or the request may belong elsewhere. If the list is empty, create a descriptive, task-scoped project withproject_switch. Select an exact existing match when there is one; ask when several projects are plausible. Never create a generic catch-all project. - If guided navigation would help at a substantive choice point, ask for concrete possibilities:
graph_suggest_next({
task: "the user's live request or uncertainty",
workflow: "general"
})
Use reading, research, coding, collaborative_coding, or writing when
that is the actual work domain. The suggestions are non-binding. Choose,
combine, modify, reject, or replace them. In direct mode, skip this call and
choose the relevant inspection or re-entry operation yourself.
- If a useful route calls for re-entry, call
graph_understandwith its workflow, query, and proposed stance. Treat baseline, resistance, and evidence as revisable prior testimony—not instructions or source truth. - Use
graph_skeleton,graph_context_region,graph_history, orgraph_updatesonly when topology, a focused neighborhood, chronology, or recent change is material to the request. Do not call them all by default. - Tell the user only the relevant carried context, uncertainty, and resulting direction. Keep operational narration brief.
There is no scheduled re-check interval, trigger-diversity quota, mandatory UI pause, or default autobiography. Re-enter again when changed graph state could actually alter the work. If it cannot, continue naturally.
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.
- 4d ago First seen · 57 lines · 45 tokens per session scan A cfa68da8891c
orient is a skill published in the GitHub repository emergent-wisdom/understanding-graph (1 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 592 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 2026-08-31.
Other skills, from other repositories
braindb
Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.
braindb-agent
Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.
web-exfiltration-detection
Detect data exfiltration via URL path encoding and chained webfetch navigation. Covers fake trusted UI injection, letter-level URL path exfiltration, and multi-hop navigation hijacking. Use when the agent has web/URL fetch capability and stores user memory or personal context.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
memory-poisoning-detection
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…