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 agentmods add skills/goldziher/basemind/basemind-clinpx skills add Goldziher/basemind --skill basemind-cligit clone --depth 1 https://github.com/Goldziher/basemindWhat 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 | $0.00066 | $0.02052 |
| Opus 5 | $0.00033 | $0.01026 |
| Sonnet 5 | $0.00013 | $0.00410 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
basemind-cli 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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
basemind CLI — the scriptable interface
basemind has two equally-weighted surfaces: MCP (interactive tool calls) and CLI (scriptable commands).
They share the same machine-global cache (Linux ~/.local/share/basemind/, macOS
~/Library/Application Support/basemind/; override BASEMIND_DATA_HOME) and are safe to run
alongside each other. Reach for the CLI
when you're scripting, batching queries, running in headless environments, or CI.
Capabilities
- Code map across 300+ languages — tree-sitter outlines, symbol search, references, callers, call graphs, implementations, dependents.
- Full-text + symbol search — indexed regex over content and substring symbol lookup.
- Git intelligence — history, blame, and structural diffs at symbol resolution, plus churn.
- Document RAG over 90+ file formats — PDFs, Office, HTML, email, images (OCR) → semantic search.
- Shared memory — per-repo, scope-keyed key-value + semantic memory across sessions.
- Web crawl — scrape / follow-link crawl into the searchable document store.
- Cache management — stats, garbage collection, selective and full clears.
When to reach for it
- Running in headless environments or CI pipelines.
- Batching multiple queries without interactive delays.
- Integrating basemind into shell scripts or non-MCP tooling.
- Controlling tool routing explicitly (no agent routing decisions).
- Clearing caches destructively (only the CLI allows
--component all).
basemind first, shell/grep/git fallback. Prefer basemind code / graph over reading files, over
grep/rg, and over naked git: use it for code parsing (outlines, references, callers), git
history / blame / diffs (basemind git), document extraction / RAG / keyword + entity (NER) /
summary (basemind memory documents), and web scraping / crawling / sitemaps
(basemind web scrape / crawl / map). Drop to raw shell, grep, or git only when no basemind
command covers the question.
Command routing (copy this into your mental model)
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.
- 3d ago First seen · 168 lines · 66 tokens per session scan A 630926dcf240
basemind-cli is a skill published in the GitHub repository Goldziher/basemind (91 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 2,052 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
octocode-benchmark
Use when planning, running, grading, or reporting the by-hand Octocode research benchmark — pairwise matchups (Octocode anchor vs one baseline: gh+RTK, gh+Headroom, or plain gh) over markdown questions, with a fresh isolated runner agent per (question, arm, pass), one blind judge per question grading two answers X/Y…
x-ray
Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
octocode-roast
Use when code needs a blunt evidence-backed roast or memorable critique: smell inventory, debt ranking, hot-path autopsy, savage/diff review, security or performance sins, or practical redemption paths. Phrases like roast this, brutal review, top sins, cleanup debt. Polite evidence-first PR review → octocode-research.
lsp-format-code
Format a file or selection using the language server's formatter. Use before committing to apply consistent style, or after generating code to clean up indentation and spacing. Supports full-file and range-based formatting.