reweave-operator

reweave-operator is a skill for Claude Code, Codex from vnmoorthy/reweave. It costs 62 tokens per session (410 once invoked), scanned A, original, MIT.

An operator guide for Reweave, a system that monitors web-data pipelines and helps repair them when a website changes its structure.

In plain words
What is it for?
It is for checking source health, running pipeline checks, reviewing repair evidence, and approving or rejecting proposed fixes.
Why use it?
It helps you find broken data sources, understand proposed selector repairs, and keep a person in control before production extraction rules change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for checking source health, running pipeline checks, reviewing repair evidence, and approving or rejecting proposed fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vnmoorthy/reweave/reweave-operator
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.

Any agent
npx skills add vnmoorthy/reweave --skill reweave-operator
Clone the repo
git clone --depth 1 https://github.com/vnmoorthy/reweave

Made for: Claude Code, Codex.

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 reweave-operator

README.md
[![agentmods](https://agentmods.dev/badge/skills/vnmoorthy/reweave/reweave-operator.svg)](https://agentmods.dev/skills/vnmoorthy/reweave/reweave-operator)
Your own site
<a href="https://agentmods.dev/skills/vnmoorthy/reweave/reweave-operator"><img src="https://agentmods.dev/badge/skills/vnmoorthy/reweave/reweave-operator.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 410 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 $0.00062 $0.00410
Opus 5 $0.00031 $0.00205
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 6d ago against content hash e10cc8cc6e89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

reweave-operator 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 6d 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.

skills/reweave-operator/SKILL.md · 35 lines

What it actually says

Reweave operator

You are operating a fleet of self-healing web data pipelines through the reweave MCP server.

Operating loop

  1. list_sources — check fleet health first. A broken status means an open structural-drift incident.
  2. run_pipeline(source_id) — one observe/extract/assess cycle. On drift the Surgeon auto-synthesizes a repair and parks it at the approval gate; the run result tells you whether a proposal was created.
  3. list_pending_heals — read the proposal's diffs (old → new selector per field), validation (confidence, per-field golden match rates), and evidence before saying anything to the operator.
  4. Summarize the repair for the human in one paragraph: what broke, what the new selectors are, and the validation numbers. Then — and only with their explicit go-ahead — call approve_heal with their name as actor.

Hard rules

  • NEVER call approve_heal or reject_heal without an explicit instruction from the human naming the decision. These deploy or discard production extraction specs.
  • If a proposal's validation confidence is below 90%, recommend rejection and a manual look, even if the human seems inclined to approve.
  • When run_pipeline reports drift but no proposal (Surgeon escalation), gather the Sentinel's failure list and present it — do not retry in a loop.
  • Quote impact numbers only from impact_report, never from memory.
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. 6d ago First seen · 35 lines · 62 tokens per session scan A e10cc8cc6e89

Subscribe to this mod's changes

reweave-operator is a skill published in the GitHub repository vnmoorthy/reweave (0 stars, last pushed 8d ago), licensed MIT. It adds 62 tokens to every session and 410 once invoked, about $0.0003 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.