orient

A command for producing a focused briefing from project knowledge, research, journal entries, and a memory graph. It loads information about a requested topic rather than the entire knowledge base.

In plain words
What is it for?
Use it to ask what the project knows about a topic, entity type, or time period, such as recent evidence or unresolved tensions.
Why use it?
It helps you recover relevant project context without searching every note or past record manually.

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/harnessprotocol/harness-kit/orient
Any agent
npx skills add harnessprotocol/harness-kit --skill orient
Clone the repo
git clone --depth 1 https://github.com/harnessprotocol/harness-kit

Made for: Claude Code, Codex.

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,418 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 $0.00080 $0.02418
Opus 5 $0.00040 $0.01209
Sonnet 5 $0.00016 $0.00484
Haiku 4.5 $0.00008 $0.00242

Measured 2d ago against content hash d091f700ecd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

plugins/orient/skills/orient/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Topic-Focused Orientation

Overview

Produce a focused orientation briefing for a specific topic by searching across the knowledge graph, knowledge files, journal entries, and research index. Designed for targeted context loading — get only what's relevant instead of everything.

Core principles:

  1. Targeted, not exhaustive. Only return information related to the requested topic.
  2. Graceful degradation. If MCP Memory Server is not connected, skip graph sections. Knowledge files and research still work.
  3. Conversation output. Briefing goes to the conversation, not files. The user can ask to save.
  4. Token-conscious. Output stays between ~800-2000 tokens. Orientation briefing, not document dump.

When to Use

User types /orient followed by:

  • Topic keyword → search everything for that topic (membrain, data engineering)
  • Entity type name → search graph for that type (desires, open tensions)
  • Time qualifier → show recent entries (recent, last week, today)
  • Combination → compound search (recent membrain, desires and tensions)

Invocation Examples

/orient membrain
/orient desires and tensions
/orient recent evidence
/orient the streaming migration project
/orient data engineering

Workflow Order

Follow in order. Skip a step only when its required component is absent (e.g., MCP not connected → skip Graph).


Step 1: Parse Input

Classify the argument into one or more of:

Type Detection Example
Entity type Matches known graph type (case-insensitive): Desire, Tension, Evidence, Project, Research, Concept, Value, Idea, Procedure, Question, Goal desires, open tensions
Time qualifier Contains: "recent", "latest", "last week", "today", date patterns (YYYY-MM-DD) recent evidence
Topic keyword Everything else — natural language membrain, data engineering

Time qualifier definitions (applies to journal only — graph searches are always full-graph unless the query is explicitly temporal):

  • "today" → today's journal entry only
  • "recent" / "latest" → journal entries from the last 1 month
  • "last week" → journal entries from the last 7 days
  • Specific date (YYYY-MM-DD) → that journal entry
  • User-specified timeframe → use that instead

Read the full file on GitHub · 218 lines

Files

What ships with it

1 file 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 · 218 lines · 80 tokens per session scan A d091f700ecd0

Subscribe to this mod's changes

orient is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 80 tokens to every session and 2,418 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens

epd-to-spec

Write CSI specification language for EPD submittals and sourced GWP limits. Use to add embodied-carbon or EPD requirements to specs; not to parse, find, or compare EPDs.

AlpacaLabsLLC/skills-for-architects · 45 tokens

occupancy-calculator

Calculate code occupant loads by area with gross/net factors and jurisdiction checks. Use for "how many people can this space hold," IBC Table 1004.5, egress inputs, or occupancy-load reports; not for workplace headcount planning.

AlpacaLabsLLC/skills-for-architects · 55 tokens

workplace-programmer

Build office space programs through guided workplace strategy: area splits, room schedules, and planned seat counts. Use to program or size a workplace; not for code occupant-load calculations.

AlpacaLabsLLC/skills-for-architects · 40 tokens

workplan

Create a durable, execution-ready work plan for repository changes, operations, research, or AEC project delivery. Use when the user asks to plan, scope, sequence, coordinate, or break down multi-step work before acting. Do not use for floor plans, site plans, space planning, zoning calculations, building-code…

AlpacaLabsLLC/skills-for-architects · 72 tokens

zoning-analysis-nyc

Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.

AlpacaLabsLLC/skills-for-architects · 57 tokens