auto_shaper_wiki

auto_shaper_wiki is an agent for coding agents from theafh/ai-modules. It costs 132 tokens per session (17,794 once invoked), scanned A, original, MIT.

An agent that audits a repository's wiki, runs its checks, and automatically fixes safe, clear problems such as invalid metadata, broken links, wrong tags, and pages that should be split.

In plain words
What is it for?
Use it to check wiki structure, repair deterministic errors, split oversized or mixed-topic pages, and report changes and unresolved conflicts.
Why use it?
It reduces the manual effort of finding and repairing wiki-quality issues while leaving genuinely ambiguous decisions for the user.

Agent

Part of the knowledge_management plugin — 6 skills, 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/theafh/ai-modules/auto_shaper_wiki
Clone the repo
git clone --depth 1 https://github.com/theafh/ai-modules

Or install knowledge_management, the plugin that ships this one along with the rest of its 6 skills, 1 agent.

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 auto_shaper_wiki

README.md
[![agentmods](https://agentmods.dev/badge/agents/theafh/ai-modules/auto_shaper_wiki.svg)](https://agentmods.dev/agents/theafh/ai-modules/auto_shaper_wiki)
Your own site
<a href="https://agentmods.dev/agents/theafh/ai-modules/auto_shaper_wiki"><img src="https://agentmods.dev/badge/agents/theafh/ai-modules/auto_shaper_wiki.svg" alt="Measured on agentmods" height="20"></a>
Per session 132 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 17,794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00132 $0.17794
Opus 5 $0.00066 $0.08897
Sonnet 5 $0.00026 $0.03559
Haiku 4.5 $0.00013 $0.01779

Measured 4d ago against content hash 616bffa17aef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto_shaper_wiki 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 4d 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.

plugins/knowledge_management/agents/auto_shaper_wiki.md · 1,532 lines

How it starts

The opening of the file, as written. The whole thing — 1,532 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Shaper Wiki

<remediation_contract> The one governing rule for how the agent resolves what it finds: autonomously apply every fix that is safe and deterministic, and surface only genuine judgment calls. A fix is safe and deterministic when it loses no meaning, invents no value, and resolves no genuine ambiguity — the corrected state is recoverable from what is already present. Apply every such fix in place and record it in the per-file change report (<report_changes>). Route everything else — a contradiction, a conflict between two real values, a genuinely broken or ambiguous case — to the user through the existing contested-page protocol (<contradictions_surfaced>, <fix_contested_page>, <leave_contested_pages>), never guessing a resolution. This makes explicit what the agent already does across its per-check fix moves; stating it once keeps every check — origin-field handling included — from re-deriving it and drifting. It is what makes the agent safe to run unattended: nothing is fabricated, no genuine ambiguity is resolved silently, and everything done is reported. </remediation_contract>

<orient_first_top> Read $WIKI/SCHEMA.md once at the start of the audit. The schema declares the domain, page-type enum, tag taxonomy, and conventions every fix must honor. The full orientation pass — SCHEMA + index + recent log + canonical references — is covered in <orient> below; this top-line note exists so the SCHEMA read is never skipped or deferred. </orient_first_top>

Read the full file on GitHub · 1,532 lines

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. 4d ago First seen · 1,532 lines · 132 tokens per session scan A 616bffa17aef

Subscribe to this mod's changes

auto_shaper_wiki is an agent published in the GitHub repository theafh/ai-modules (38 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 17,794 once invoked, about $0.0007 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.