mache-explore

mache-explore is a skill for Claude Code, Codex from agentic-research/mache. It costs 27 tokens per session (870 once invoked), scanned A, original, Apache-2.0.

A filesystem mount that places structured data inside the project directory so a coding agent can browse it like ordinary files.

In plain words
What is it for?
Use it to mount a Mache data source from a schema and a directory or database file, then search or read the mounted data with normal file tools.
Why use it?
It avoids repeated permission prompts when the agent needs to inspect many files at once. It provides bulk access when individual data-reading tools are not enough.

Skill for Claude CodeCodex

Part of the mache plugin — 3 skills, 1 agent shipped together

Install

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.

agentmods
npx agentmods add skills/agentic-research/mache/mache-explore
Any agent
npx skills add agentic-research/mache --skill mache-explore
Clone the repo
git clone --depth 1 https://github.com/agentic-research/mache

Made for: Claude Code, Codex.

Or install mache, the plugin that ships this one along with the rest of its 3 skills, 1 agent.

Wrote 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.

agentmods badge for mache-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/agentic-research/mache/mache-explore.svg)](https://agentmods.dev/skills/agentic-research/mache/mache-explore)
Your own site
<a href="https://agentmods.dev/skills/agentic-research/mache/mache-explore"><img src="https://agentmods.dev/badge/skills/agentic-research/mache/mache-explore.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 870 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00027 $0.00870
Opus 5 $0.00014 $0.00435
Sonnet 5 $0.00005 $0.00174
Haiku 4.5 $0.00003 $0.00087

Measured 4d ago against content hash 91c024fceefb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mache-explore 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 4d 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.

plugin/skills/mache-explore/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mache Explore - FUSE Mount for Agent Access

Mount a mache data source inside the project directory so all file reads are auto-approved by Claude Code's permission model. Use this when you need direct filesystem access to mache-projected data (e.g., for Grep, Glob across the mount).

For most tasks, prefer the MCP tools (list_directory, read_file, search, find_callers, find_callees, get_communities) which are available automatically via the mache plugin. Use this FUSE skill only when you need bulk filesystem access.

Arguments

$ARGUMENTS

Arguments format: <schema> <data-source> [mount-name]

  • schema: Path to a mache schema JSON file (e.g., examples/go-schema.json)
  • data-source: Path to data (directory, .db file, etc.)
  • mount-name: Optional name for the mount point (default: default)

Examples:

/mache:mache-explore examples/go-schema.json .
/mache:mache-explore examples/nvd-schema.json ~/.agentic-research/venturi/nvd/results/results.db nvd

Workflow

Phase 1: Parse Arguments

Extract from $ARGUMENTS:

  • SCHEMA = first argument (required)
  • DATA_SOURCE = second argument (required)
  • MOUNT_NAME = third argument, or default if not provided

If fewer than 2 arguments, ask the user for the missing values.

Phase 2: Validate Inputs

MACHE_BIN=$(which mache 2>/dev/null) && echo "Found: $MACHE_BIN" || echo "NOT_FOUND"

If not found, ask the user for the full binary path. Then learn the CLI:

"$MACHE_BIN" --help 2>&1 | head -20

Use the --help output to determine correct flags. Do NOT assume flag names.

Validate schema and data source exist:

ls -la "$SCHEMA"
ls -la "$DATA_SOURCE"

Phase 3: Mount

mkdir -p .mache-mount/$MOUNT_NAME
grep -q '^\.mache-mount/' .gitignore 2>/dev/null || echo '.mache-mount/' >> .gitignore
"$MACHE_BIN" <flags from --help> .mache-mount/$MOUNT_NAME &
echo $! > .mache-mount/.pid
echo "mache PID: $(cat .mache-mount/.pid)"

Wait for readiness (up to 10 seconds):

for i in $(seq 1 10); do
  if ls .mache-mount/$MOUNT_NAME/ 2>/dev/null | head -1; then
    echo "Mount ready"
    break
  fi
  sleep 1
done

Read the full file on GitHub · 101 lines

Changes

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.

  1. 4d ago First seen · 101 lines · 27 tokens per session scan A 91c024fceefb

Subscribe to this mod's changes

mache-explore is a skill published in the GitHub repository agentic-research/mache (45 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 870 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

lsp-inspect

Full code quality audit for a file, package, or directory. Supports batch mode (directory walk with --top ranking), comparison mode (--diff for branch-only issues), severity calibration by blast radius, fix suggestions, and confidence tiers. Applies a check taxonomy (dead symbols, silent failures, error wrapping…

blackwell-systems/agent-lsp · 126 tokens

lsp-architecture

Generate a structural architecture overview of a codebase: languages, package map, entry points, dependency graph, and hotspots. One call for the big picture.

blackwell-systems/agent-lsp · 36 tokens

lsp-dead-code

Enumerate exported symbols in a file and surface those with zero references across the workspace. Use when auditing for dead code, cleaning up APIs, or checking which exports are safe to remove.

blackwell-systems/agent-lsp · 43 tokens

lsp-refactor

End-to-end safe refactor workflow — blast-radius analysis, speculative preview, apply to disk, verify build, run affected tests. Inlines lsp-impact + lsp-safe-edit + lsp-verify + lsp-test-correlation into one coordinated sequence.

blackwell-systems/agent-lsp · 57 tokens

lsp-safe-edit

Wrap any code edit with before/after diagnostic comparison. Speculatively previews the change first (previewedit), then applies to disk only if the error delta is acceptable. If post-edit errors appear, surfaces code actions for quick fixes. Handles single and multi-file edits.

blackwell-systems/agent-lsp · 59 tokens

lsp-understand

Deep-dive exploration of unfamiliar code — given a symbol or file, builds a complete Code Map showing type info, implementations, call hierarchy (2-level depth limit), all references, and source. Broader than lsp-explore: accepts files, synthesizes multi-symbol relationships, and produces a navigable dependency map.

blackwell-systems/agent-lsp · 69 tokens