Borrowing it
Nothing to install: this file belongs to vlasenkoalexey/tpu_performance_autoresearch_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/wikify-ingest-repo/SKILL.mdgit clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wikiWrote 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/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo)<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo"><img src="https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00108 | $0.02710 |
| Opus 5 | $0.00054 | $0.01355 |
| Sonnet 5 | $0.00022 | $0.00542 |
| Haiku 4.5 | $0.00011 | $0.00271 |
Grade A, and why
wikify-ingest-repo 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 13d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wikify-ingest-repo
Drive the deterministic wikify CLI around one LLM-in-the-loop step: concept
synthesis. The CLI does everything else (acquire, SCIP index, graph, diff,
packets, lint, assemble). You write one mechanism page per packet. Never put
synthesis in Python; never push linting into your prose.
Preconditions
wikifyis on PATH, plus the SCIP indexer for the repo's language(s):scip-pythonand the vendoredscip-clangcome fromscripts/setup-vendor.sh(see the repo's README); TS/JS, Go, and Rust indexers are installed on demand —preparedetects the language and auto-installs a missing indexer, announcing the command (pass--no-install-indexersto skip instead). If prepare reports a language was skipped anyway (install failed — e.g. scip-go needs a Go toolchain), surface that to the user rather than ignoring it: the skipped language's symbols are absent from the wiki until it's installed and prepare re-runs.
Input — invoke with the repo to ingest
You are called with a repo URL or local path (e.g. wikify-ingest-repo https://github.com/owner/myrepo), or with an existing <slug> to update.
Step 0 — bootstrap the config yourself (never ask the user to write it). Derive <slug>
from the repo (basename, minus .git). If config/<slug>.md does not already exist, create it:
---
slug: <slug>
repo: <the URL or local path>
---
No ## Concepts list is needed — discovery auto-seeds the agenda from code centrality; add seed
concepts later only to go deeper into a subsystem. If a config for that slug already exists,
reuse it (re-ingest is idempotent). Then run the Procedure below with <slug>.
Focus (lens) — settle it before synthesizing; ask only if it isn't already known. If the
config already has synthesis_focus, or the host wiki has an established lens (skim a couple of
sibling config/*.md, or the host SCHEMA.md), use that — do not re-ask a settled question.
Otherwise ASK the user for the domain angle in one line (e.g. "TPU performance — kernels,
sharding, autotune, precision") and write it into config/<slug>.md as synthesis_focus:. In a
non-interactive/batch run with no signal, proceed neutrally (no lens). The lens shapes emphasis,
never grounding.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 169 lines · 108 tokens per session scan A 6a8164efa04c
wikify-ingest-repo is a skill published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 8d ago), licensed MIT. It adds 108 tokens to every session and 2,710 once invoked, about $0.0005 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
customer_support_agent
You have access to Leeroopedia, a curated ML/AI knowledge base, via MCP tools. These are real MCP tools registered in your environment -- call them directly like any other tool. They contain framework-specific docs, code examples, API references, and best practices.
ml_inference_optimization
This document describes the Leeroopedia MCP tools available during the with-KB benchmark run. It is a standalone reference and is not fed to the agents automatically.
leeroopedia-mcp
Use Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via getpage.
self_evolve_rag
This document describes how to use the Leeroopedia MCP tools for the Self-Evolving RAG task. It is kept as a reference and is NOT included in the agent prompt.
llm_post_training
You have access to the Leeroopedia MCP tools. Use them throughout this pipeline to make informed decisions. Specifically.
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.