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/agentic-research/mache/mache-explorenpx skills add agentic-research/mache --skill mache-exploregit clone --depth 1 https://github.com/agentic-research/macheWrote 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/agentic-research/mache/mache-explore)<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>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 | $0.00027 | $0.00870 |
| Opus 5 | $0.00014 | $0.00435 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
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.
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,
.dbfile, 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 $ARGUMENTS:
SCHEMA= first argument (required)DATA_SOURCE= second argument (required)MOUNT_NAME= third argument, ordefaultif not provided
If fewer than 2 arguments, ask the user for the missing values.
Phase 2: Validate Inputs
MACHE_BIN=$(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
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.
- 4d ago First seen · 101 lines · 27 tokens per session scan A 91c024fceefb
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.
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…
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.
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.
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.
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.
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.