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 harnessprotocol/harness-kit --skill orientgit clone --depth 1 https://github.com/harnessprotocol/harness-kitWrote 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/harnessprotocol/harness-kit/orient)<a href="https://agentmods.dev/skills/harnessprotocol/harness-kit/orient"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/orient/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/harnessprotocol/harness-kit/orient"><img src="https://agentmods.dev/badge/skills/harnessprotocol/harness-kit/orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.02418 |
| Opus 5.5 | $0.00032 | $0.00967 |
| Sonnet 5.5 | $0.00016 | $0.00484 |
| Haiku 4.5 | $0.00008 | $0.00242 |
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 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 — 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:
- Targeted, not exhaustive. Only return information related to the requested topic.
- Graceful degradation. If MCP Memory Server is not connected, skip graph sections. Knowledge files and research still work.
- Conversation output. Briefing goes to the conversation, not files. The user can ask to save.
- 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
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.
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 · 218 lines · 80 tokens per session scan A d091f700ecd0
orient is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed today), licensed Apache-2.0. It adds 80 tokens to every session and 2,418 once invoked, about $0.0003 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
llm-wiki
Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate…
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…