tpu_performance_autoresearch_wiki: Skill for Claude Code

.claude/skills/wikify-ingest-repo/SKILL.md

wikify-ingest-repo is a skill for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 108 tokens per session (2,710 once invoked), scanned A, original, MIT.

A repository-ingestion procedure that turns a code repository into a searchable Markdown wiki. The wiki documents the repository's internal concepts and relationships so an agent can answer questions about the code.

In plain words
What is it for?
Use it to build or update a wiki from a repository URL, local path, or existing project, including code indexing, concept pages, links, and linting.
Why use it?
It gives the agent a grounded reference instead of making it infer the codebase from scattered source files, while checks catch incomplete or broken documentation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is vlasenkoalexey/tpu_performance_autoresearch_wiki's own configuration. It tells Claude Code how to work on tpu_performance_autoresearch_wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tpu_performance_autoresearch_wiki configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vlasenkoalexey/tpu_performance_autoresearch_wiki/main/.claude/skills/wikify-ingest-repo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vlasenkoalexey/tpu_performance_autoresearch_wiki

Made for: Claude Code.

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 wikify-ingest-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo/github.svg)](https://agentmods.dev/skills/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-ingest-repo)
Your own site
<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.

agentmods 80×15 button for wikify-ingest-repo

Your own site · 80×15
<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>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
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 5.1 $0.00108 $0.02710
Opus 5 $0.00054 $0.01355
Sonnet 5 $0.00022 $0.00542
Haiku 4.5 $0.00011 $0.00271

Measured 13d ago against content hash 6a8164efa04c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.claude/skills/wikify-ingest-repo/SKILL.md · 169 lines

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

  • wikify is on PATH, plus the SCIP indexer for the repo's language(s): scip-python and the vendored scip-clang come from scripts/setup-vendor.sh (see the repo's README); TS/JS, Go, and Rust indexers are installed on demandprepare detects the language and auto-installs a missing indexer, announcing the command (pass --no-install-indexers to 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.

Read the full file on GitHub · 169 lines

Files

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.

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. 13d ago First seen · 169 lines · 108 tokens per session scan A 6a8164efa04c

Subscribe to this mod's changes

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.