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 Cranot/roam-code --skill roamgit clone --depth 1 https://github.com/Cranot/roam-codeWrote 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/cranot/roam-code/roam)<a href="https://agentmods.dev/skills/cranot/roam-code/roam"><img src="https://agentmods.dev/badge/skills/cranot/roam-code/roam/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/cranot/roam-code/roam"><img src="https://agentmods.dev/badge/skills/cranot/roam-code/roam.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 | $0.00086 | $0.02460 |
| Opus 5.5 | $0.00034 | $0.00984 |
| Sonnet 5.5 | $0.00017 | $0.00492 |
| Haiku 4.5 | $0.00009 | $0.00246 |
Grade A, and why
roam 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 6d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roam — Codebase Comprehension Skill
Repository: https://github.com/Cranot/roam-code
Roam pre-indexes codebases into a semantic graph (symbols, dependencies, call graphs, architecture layers, git history) stored in a local SQLite DB. Query it via CLI instead of repeatedly grepping files and guessing structure.
Setup
Ensure roam-code is installed and the project is indexed:
pip install roam-code # or: pipx install roam-code
cd <project-root>
roam init # indexes codebase, creates .roam/index.db
After git pull or major changes, run roam index to refresh (incremental,
near-instant if few files changed). After large refactors: roam index --force.
Command Decision Table
Use this table to pick the right command for the situation:
| Situation | Command |
|---|---|
| First time in a repo | roam understand then roam tour |
| Need a compact codebase overview | roam map or roam minimap |
| Find a symbol by name | roam search <pattern> |
| Need files to read for a symbol | roam context <symbol> |
| Inspect a file's structure | roam file <path> |
| Inspect a directory | roam module <path> |
| Before modifying a symbol | roam preflight <symbol> |
| What breaks if I change X? | roam impact <symbol> |
| Blast radius of uncommitted changes | roam diff |
| Debugging a failure | roam diagnose <symbol> |
| Which tests cover a symbol? | roam affected-tests <symbol> |
| Check codebase health | roam health |
| Find hotspots (churn x complexity) | roam weather |
| Detect dead/unused code | roam dead |
| PR risk assessment | roam pr-risk |
| Find dependency paths | roam trace <source> <target> |
| Who calls/imports this? | roam uses <symbol> (alias: roam refs) |
| Find every reference to X (replaces multi-shape grep) | roam refs <symbol> |
| Algorithm anti-patterns | roam algo |
| Side effects of a function | roam effects <symbol> |
| Safe to delete? | roam safe-delete <symbol> |
| Simulate a refactor | `roam simulate move |
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.
- 6d ago Changed ccc01fb57f0b
- 1mo ago First seen · 276 lines · 86 tokens per session scan A a78d680a0947
roam is a skill published in the GitHub repository Cranot/roam-code (517 stars, last pushed 2d ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,460 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 2026-08-30.
Other skills, from other repositories
agentmap
Use for TypeScript/JavaScript codebase navigation — symbol lookup, blast radius, reuse checks, and repo orientation. Prefer agentmap before serial grep when exploring imports, exports, or where a symbol lives. Package is @raymondchins/agentmap (not the unrelated npm package agentmap).
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…
dekko-refactor
List every site a rename, move, or signature change must touch before editing, then prove nothing was missed after. Trigger when about to rename a function, method, class or type, rename or move a file or module, change a parameter list or return type, move a symbol between files, or remove a symbol, in a repo with a…
dekko-debug
Work a stack trace, exception, or error report from dekko's map instead of reading each frame's file. Trigger when given a traceback, an exception type or message, a failing test's error, or a question like "why does X raise", "who handles this error", "how does control get from A to B", or "where is this env var…
dora
Query codebase using dora CLI for code intelligence, symbol definitions, dependencies, and architectural analysis.
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.