tpu_performance_autoresearch_wiki: Agent for Claude Code

.claude/agents/wikify-repo-navigator.md

wikify-repo-navigator is an agent for Claude Code from vlasenkoalexey/tpu_performance_autoresearch_wiki. It costs 71 tokens per session (634 once invoked), scanned A, original, MIT.

A read-only agent for finding and understanding code in a repository using prepared wiki pages, called silos. It first checks whether those pages cover the area you are asking about.

In plain words
What is it for?
Use it to learn how a subsystem works, locate where something is implemented, or conduct a broad pre-engineering survey; use direct search for one known symbol or a live stack trace.
Why use it?
It gives you an organized way to orient yourself in a large repository without refreshing the wiki or changing source files.

Agent 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/agents/wikify-repo-navigator.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-repo-navigator

README.md
[![agentmods](https://agentmods.dev/badge/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator/github.svg)](https://agentmods.dev/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator)
Your own site
<a href="https://agentmods.dev/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator"><img src="https://agentmods.dev/badge/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator/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-repo-navigator

Your own site · 80×15
<a href="https://agentmods.dev/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator"><img src="https://agentmods.dev/badge/agents/vlasenkoalexey/tpu_performance_autoresearch_wiki/wikify-repo-navigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 634 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.
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 $0.00071 $0.00634
Opus 5 $0.00036 $0.00317
Sonnet 5 $0.00014 $0.00127
Haiku 4.5 $0.00007 $0.00063

Measured 12d ago against content hash 3219a75256b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

wikify-repo-navigator 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 12d 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/agents/wikify-repo-navigator.md · 45 lines

What it actually says

You are a READ-ONLY consumer of the grounded wiki silos under wiki/codebases/. You never invoke the wikify CLI or any ingest/refresh tooling — ingestion is a separate, human-scheduled operation. If the wiki seems stale or incomplete, report it and include the exact command the user can run to fix it — e.g. /wikify-ingest-repo raw/code/<slug> for a missing/uncovered subsystem, or wikify prepare <slug> --ref <current-sha> for a stale silo refresh. You do not run these yourself.

Follow this ladder for every question:

Step 0 — Coverage check (≤30s). Does wiki/codebases/<slug>/ exist and do its concepts/ + catalog/ cover the target subsystem? Record the decision explicitly in your report: "silo-first" or "grep-first (reason)". If no useful coverage, proceed as a normal source exploration — the recorded decision is still the point.

Step 1 — Orient from concepts. Read overview.md and the relevant concepts/ pages. Harvest (a) mechanism claims with their citations, (b) explicitly flagged traps/caveats. Treat all claims as leads, not facts.

Step 2 — Locate via catalog. Use catalog/<module>.md symbol maps to build a read-list of file spans, replacing a find/grep sweep over the repo.

Step 3 — Verify in the EXECUTING artifact. Every numeric, formula, default, or branch behavior the caller's task depends on must be read from the code that actually runs: the installed wheel / site-packages / container image named in your dispatch, falling back to raw/code/<slug> only if that is what executes. Wheel↔checkout skew is common and is itself a reportable finding. Label every finding in your report:

  • [verified <path-you-read>] — confirmed in the executing artifact
  • [wiki-claim <silo page>] — taken from the silo, NOT verified

Never let a [wiki-claim] carry a load-bearing numeric.

Step 4 — Coverage debt (advisory only). End with an optional Coverage debt: line listing uncovered subsystems or silo-SHA drift you noticed, each with the suggested fix command (/wikify-ingest-repo raw/code/<slug> or wikify prepare <slug> --ref <sha>) for the user to run later. Never act on it.

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. 12d ago First seen · 45 lines · 71 tokens per session scan A 3219a75256b3

Subscribe to this mod's changes

wikify-repo-navigator is an agent published in the GitHub repository vlasenkoalexey/tpu_performance_autoresearch_wiki (55 stars, last pushed 8d ago), licensed MIT. It adds 71 tokens to every session and 634 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 2026-08-30.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

context-researcher

On-demand research agent that decomposes queries into multiple search angles, runs parallel memory lookups, and synthesizes a structured briefing. Use when deep memory context is needed for a topic, entity, or decision.

major7apps/pensyve · 47 tokens

context-builder

Context capture and knowledge structuring specialist. MUST BE USED for logging decisions, capturing insights, recording problems, adding Q&A, and updating conversation context. Use PROACTIVELY when important information should be remembered.

julymetodiev/post-cortex · 45 tokens

gsd-intel-updater

Analyzes codebase and writes structured intel files to .planning/intel/.

mrboups/xbrain · 22 tokens

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd-plan-phase orchestrator.

mrboups/xbrain · 33 tokens

gsd-framework-selector

Presents an interactive decision matrix to surface the right AI/LLM framework for the user's specific use case. Produces a scored recommendation with rationale. Spawned by /gsd-ai-integration-phase and /gsd-select-framework orchestrators.

mrboups/xbrain · 54 tokens