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 the-metafactory/soma --skill orienteergit clone --depth 1 https://github.com/the-metafactory/somaWrote 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/the-metafactory/soma/orienteer)<a href="https://agentmods.dev/skills/the-metafactory/soma/orienteer"><img src="https://agentmods.dev/badge/skills/the-metafactory/soma/orienteer.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01594 |
| Opus 5 | $0.00043 | $0.00797 |
| Sonnet 5 | $0.00017 | $0.00319 |
| Haiku 4.5 | $0.00009 | $0.00159 |
Grade A, and why
orienteer 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orienteer
A loose idea has arrived — too big for one agent session, and wrapped in fog: the way from here to the destination isn't visible yet. Orienteering is about finding that way, not charging at the destination. This skill charts the way as a shared map on the work graph, then works its decision nodes — questions whose resolution is a decision, not slices of a build to execute — one at a time until the route is clear.
The name is the practice: orienteering is checkpoint-based map navigation, and the route only counts if you pass the controls.
Fast path
Walking an existing map is the common case. Its root node id is the map:
soma graph frontier <root> # what is takeable: open, unassigned, unblocked
soma graph claim <id> # claim ONE, before any work
soma graph node <id> # read it (body included), and any node it references
# … resolve it …
soma graph close <id> --resolution-file <path> --gist "<one line>"
soma graph decisions <root> --write # re-derive the map's decision index from receipts
The gist rides the receipt and decisions --write projects every closed node's
gist into the map body — the map's index is derived, never hand-edited. Then
graduate any fog the answer sharpened. Read Workflows/WalkTheMap.md before
step one.
When to use
- A loose idea too big to hold in one session, where the route is unclear —
not just the work. Chart it:
Workflows/ChartTheMap.md. - An existing map with open nodes. Walk it:
Workflows/WalkTheMap.md.
Do not use when the way to the destination is already clear and the whole journey fits one session — you don't need a map, you need to do the work. If charting surfaces no fog, say so and stop.
The verbs
Every graph operation is a soma graph verb. Never reach past them to the
tracker's own CLI — the verbs carry the rules (structural validation, cycle
rejection, claim tie-break, the hollow-close refusal), and a raw tracker write is
those rules not running. The backend hides behind the CLI, which is what makes
this doctrine tracker-agnostic by construction.
What ships with it
5 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.
- 8d ago First seen · 119 lines · 85 tokens per session scan A 330e4188412a
orienteer is a skill published in the GitHub repository the-metafactory/soma (8 stars, last pushed 3d ago), licensed MIT. It adds 85 tokens to every session and 1,594 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…