Litho is a Rust-based AI documentation generator that analyzes a codebase and produces architecture documentation in the C4 model format. Developers, architects, and technical leads use it to create and maintain diagrams and code-level documentation, while the catalogue provides skills for working with the project.
Borrowing it
Nothing to install: this file belongs to sopaco/deepwiki-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sopaco/deepwiki-rs/main/.agents/skills/terrain-knowledge-skill/SKILL.mdgit clone --depth 1 https://github.com/sopaco/deepwiki-rsWrote 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/sopaco/deepwiki-rs/terrain-knowledge-skill)<a href="https://agentmods.dev/skills/sopaco/deepwiki-rs/terrain-knowledge-skill"><img src="https://agentmods.dev/badge/skills/sopaco/deepwiki-rs/terrain-knowledge-skill/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/sopaco/deepwiki-rs/terrain-knowledge-skill"><img src="https://agentmods.dev/badge/skills/sopaco/deepwiki-rs/terrain-knowledge-skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00905 |
| Opus 5.5 | $0.00014 | $0.00362 |
| Sonnet 5.5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
terrain-knowledge-skill 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- terrain-knowledge-skill — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terrain Knowledge Skill
Terrain stores AI knowledge assets under .terrain/ in this repository (not a global ~/.terrain/knowledge directory). The desktop app registry at ~/.terrain/registry.json only maps slugs → repo paths.
Load rtk-skill when you need to run shell commands during investigation (git, grep repomix file, tests). Resolve tools via conventional paths (~/.terrain/bin/…) with bunx/npx fallback — see rtk-skill / codegraph-skill.
Knowledge layers (mandatory order)
-
Architecture —
.terrain/agent/context.md- Module map, core flows, system boundaries, tech stack
- Check
.terrain/agent/context-meta.jsonormeta.jsonfor asset timestamps - Read directly (short); no RTK needed
-
Private domain —
.terrain/knowledge/**/*.md- Business glossary, internal frameworks, APIs, scaffolding guides
- Team-maintained markdown; read in filename sort order when surveying
-
Structured meta —
.terrain/agent/meta-inputs.md- Compiled from
terrain-meta.jsonandknowledge/scans
- Compiled from
-
Source index — see
repomix-context-skill- Local
.terrain/agent/repomix.md(gitignored; regenerate via Terrain scan)
- Local
Knowledge freshness (mandatory before architecture answers)
Before trusting context.md for module/architecture questions:
~/.terrain/bin/terrain tools freshness --project <slug>
# or: bunx @terrain-ai/cli tools freshness --project <slug>
This recomputes when stale and writes .terrain/.meta/freshness.json. Do not only read that JSON statically — it is a local cache snapshot.
| Score | Rule |
|---|---|
< 50 |
Do not rely on macro context; use repomix-context-skill |
50–69 |
Cross-check with repomix grep or codegraph-skill |
≥ 70 |
Architecture context is generally reliable |
On conflict: repomix source slices > codegraph > agent/context.md > human/
For symbol impact/callers, also see codegraph-skill (CodeGraph status can lie; use terrain tools codegraph-drift).
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 · 91 lines · 36 tokens per session scan A 7f90bb535b36
terrain-knowledge-skill is a skill published in the GitHub repository sopaco/deepwiki-rs (3,143 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 905 once invoked, about $0.0001 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 2026-09-15.
Other skills, from other repositories
krouter-obsidian
KRouter Obsidian — route knowledge-dependent tasks to the smallest current evidence set in an Obsidian vault using deterministic local search. Use when a request depends on durable user preferences, prior corrections or superseded claims, long-term project history or results, reusable methods or evidence, or the…
knowz-amend
Apply a targeted server-side edit to an existing Knowz vault item without retyping the whole entry. Use when the user describes a delta — fix a typo, add a line, change a tag, append a caveat — to knowledge that already exists in a vault.
knowz-save
Capture decisions, patterns, conventions, workarounds, and durable learnings to Knowz vaults. Use when the user shares an insight worth keeping or explicitly asks to save knowledge.
knowz-flush
Flush idempotent queued knowledge operations (create, amend, update) from the project-root knowz-pending.md queue. Use when MCP is back after a failed save/amend, or when the user asks to replay pending captures.
knowz-setup
Connect Knowz MCP and create vault routing files. Use after installing the Knowz plugin, for first-time vault mapping, or when tools are missing after setting KNOWZAPIKEY.
knowz-auto
Lightweight Knowz intent routing for Grok Bot and Cursor. Use when the user's message looks like a knowledge lookup, a save-worthy durable insight, or a targeted edit to an existing vault item.