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 agentic-research/mache --skill authoring-schemasgit 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/authoring-schemas)<a href="https://agentmods.dev/skills/agentic-research/mache/authoring-schemas"><img src="https://agentmods.dev/badge/skills/agentic-research/mache/authoring-schemas.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.01688 |
| Opus 5 | $0.00056 | $0.00844 |
| Sonnet 5 | $0.00022 | $0.00338 |
| Haiku 4.5 | $0.00011 | $0.00169 |
Grade A, and why
authoring-schemas 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mache:authoring-schemas — Write a mache projection schema
A mache schema (api/schema.go) projects data into a tree: Topology → Node (dirs) → Leaf (files). There are two dialects and the first decision is which you're in:
| Source | Walker | Selector dialect | Path |
|---|---|---|---|
| source code (.go, .py, …) | tree-sitter / ASTWalker | tree-sitter S-expressions: (kind field: (child) @cap) @scope |
examples/go-schema.json |
| data (.db, .json) | JSONPath (ojg) | JSONPath: $, $[*], $.item.field[*] |
examples/{nvd,kev}-schema.json |
Start by copying the closest example and editing — never write from scratch.
Schema shape (the fields that matter)
Topology { version, table?, nodes[], file_sets?, diagrams? }
Node { name, selector?, refs?, language?, children[], files[], skip_self_match? }
Leaf { name, content_template, content_source?, attributes? }
nameis a Go text/template rendered against the match — it can be a literal (functions), a field ({{.name}}), or a computed expression ({{replace .item.X ":" " "}}). Computed names become directory names.selectorpicks matches.$is the wildcard "everything at this level" (used for grouping dirs likefunctions/,types/).content_templaterenders a leaf's bytes. Thesourceleaf conventionally uses{{.scope}}— the matched construct's full source text.refsare template strings; each rendered token callsAddRef(token, nodeID)→ powerscallers/.
Tree-sitter dialect (source code) — gotchas
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.
- 8d ago First seen · 79 lines · 111 tokens per session scan A 6eb2bc65c994
authoring-schemas is a skill published in the GitHub repository agentic-research/mache (45 stars, last pushed 3d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,688 once invoked, about $0.0006 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-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-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.
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-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-edit-export
Safe workflow for editing exported symbols or public APIs. Use when changing a function signature, modifying a public type, or altering any symbol used outside its own package — finds all callers first so nothing breaks silently.