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/danielc000/loom/graphifynpx skills add DanielC000/loom --skill graphifygit clone --depth 1 https://github.com/DanielC000/loomWhat 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 | $0.00075 | $0.00881 |
| Opus 5 | $0.00037 | $0.00441 |
| Sonnet 5 | $0.00015 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
graphify 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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
graphify
graphify builds a local, code-only call graph with tree-sitter — no API key, no LLM backend, no
token cost. Use it as a forward-orientation aid: given a symbol, see what it calls and how two
symbols connect. It is fast and accurate for that.
The one thing to internalize: graphify is strong going forward (explain / path) and
unreliable going backward (affected — "what breaks if I change X"). Treat forward queries as
trustworthy orientation and reverse queries as a lead to confirm with grep — never as ground truth.
Setup (opt-in — assume it's present)
One-time, human-installed like any host tool: uv tool install graphifyy (or pipx install graphifyy,
or pip install graphifyy). This skill assumes it's already there. If graphify isn't on PATH, say so
and fall back to grep/Read — don't try to install it yourself.
Build the graph (code-only)
graphify update <dir>
Point <dir> at your source root (e.g. src). This writes <dir>/graphify-out/graph.json. Only ever
use update. Never run extract or point it at a semantic/LLM backend, and never pass an API key —
code-only keeps it free and local. Rebuild after substantial code changes; the graph is a snapshot.
Use it — forward orientation (the strength)
Pass --graph <dir>/graphify-out/graph.json to each query.
graphify explain "<Symbol>"— what this symbol touches: its outgoing calls and immediate neighbors. The go-to "what does this do / what does it reach" query.graphify path "<A>" "<B>"— how two symbols connect, if they do. Good for "does this handler actually reach that writer".
The affected warning (load-bearing)
graphify affected "<Symbol>" claims to list callers ("what depends on this"). It under-reports, and
silently — a confident-looking short answer that misses real callers. It does not build caller edges
for method calls on a locally-constructed instance (const x = new Foo(); x.method()) or on a
closure/parameter receiver (a callback closing over an injected service). So a method that is called
can come back "No affected nodes found".
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.
- yesterday First seen · 67 lines · 75 tokens per session scan A 6dcc697a70d3
graphify is a skill published in the GitHub repository DanielC000/loom (7 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 881 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
package-author
当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等，或给了散乱脚本/目录要整理成可上传 zip 时，用本技能把内容规范成 plugin-protocol 标准包（补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名）。.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.