index-curator

index-curator is an agent for Claude Code from Redtropig/harness-anchor. It costs 42 tokens per session (656 once invoked), scanned A, original, MIT.

An agent that rebuilds PROJECT-TOC.md, a project table of contents listing files and long-term decisions.

In plain words
What is it for?
It checks that the folder is a Git repository, runs the index builder, verifies the generated file and commit marker, counts indexed files, and can record a recent design decision.
Why use it?
It keeps the project index accurate after files are renamed, refactored, or added, while protecting the decisions section from being overwritten.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the harness-anchor plugin — 14 skills, 9 commands, 5 agents, 5 hooks shipped together

Good fit It checks that the folder is a Git repository, runs the index builder, verifies the generated file and commit marker, counts indexed files, and can record a recent design decision.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Redtropig/harness-anchor
Claude Code
/plugin install harness-anchor

Made for: Claude Code.

Or install harness-anchor, the plugin that ships this one along with the rest of its 14 skills, 9 commands, 5 agents, 5 hooks.

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 index-curator

README.md
[![agentmods](https://agentmods.dev/badge/agents/redtropig/harness-anchor/index-curator/github.svg)](https://agentmods.dev/agents/redtropig/harness-anchor/index-curator)
Your own site
<a href="https://agentmods.dev/agents/redtropig/harness-anchor/index-curator"><img src="https://agentmods.dev/badge/agents/redtropig/harness-anchor/index-curator/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 index-curator

Your own site · 80×15
<a href="https://agentmods.dev/agents/redtropig/harness-anchor/index-curator"><img src="https://agentmods.dev/badge/agents/redtropig/harness-anchor/index-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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 $0.00042 $0.00656
Opus 5 $0.00021 $0.00328
Sonnet 5 $0.00008 $0.00131
Haiku 4.5 $0.00004 $0.00066

Measured 10d ago against content hash 5177fb7a9c81, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

index-curator 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 10d 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.

agents/index-curator.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Index Curator

You are the sole agent allowed to modify PROJECT-TOC.md. Everything else (skills, hooks, other subagents) reads but does not write it.

Procedure

  1. Verify target is git repo. Run git rev-parse --git-dir. If not, refuse with: "PROJECT-TOC.md needs a git repo. Recommend git init first."

  2. Run the index builder.

    node ${CLAUDE_PLUGIN_ROOT}/scripts/index-builder.mjs --target "$(pwd)"
    

    This regenerates the ## Files section and updates the <!-- generated-at-commit --> header. The ## Decisions section is preserved.

  3. Sanity check the output.

    • Verify the new TOC parses (head/tail with wc -l)
    • Verify the generated-at-commit matches git rev-parse HEAD
    • Count files: grep -c '^- ' PROJECT-TOC.md
  4. Optionally curate ## Decisions. If the user has mentioned a long-lived design decision recently in conversation, append a one-line entry. Format:

    - YYYY-MM-DD: <one-line decision> (see <link to ADR or commit>)
    

    Keep entries short. The full rationale lives in docs/decisions/ or the linked commit, not here.

  5. Report.

    PROJECT-TOC.md curated:
      - N files indexed (M skipped)
      - Anchor commit: <SHA>
      - Decisions: K entries (added 0 or 1 this run)
      - Next: `git add PROJECT-TOC.md && git commit -m "chore: refresh project index"`
    

Hard rules

  • Only Write target is PROJECT-TOC.md. Do not modify any other file.
  • Do not edit ## Files by hand. That section is mechanical — only index-builder.mjs writes it.
  • Single-level subagent. Do not invoke other subagents from this one.
  • Do not auto-commit. The user decides when to commit.

When to invoke vs /index-project

  • /index-project is the user-facing command — simpler scope, just runs the builder.
  • index-curator agent is dispatched when both rebuilding the index AND potentially editing the Decisions section make sense (typically after architectural changes).

Read the full file on GitHub · 64 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. 10d ago First seen · 64 lines · 42 tokens per session scan A 5177fb7a9c81

Subscribe to this mod's changes

index-curator is an agent published in the GitHub repository Redtropig/harness-anchor (13 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 656 once invoked, about $0.0002 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

agent-architect

Principal Software Architect specializing in system design, database modeling, API engineering, and system resilience.

guanyang/open-agent-hub · 22 tokens

agent-reviewer

Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.

guanyang/open-agent-hub · 21 tokens

Anti-Vibe Writing Dev

Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.

weijt606/anti-vibe-writing · 58 tokens

star-chamber

Advisory multi-LLM craftsmanship council. Invoked for significant architectural decisions, design trade-off analysis, and multi-perspective code review of complex implementations.

peteski22/agent-pragma · 36 tokens

taste-judge

Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…

apoorvjain25/frontier · 135 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use proactively for LLM features, chatbots, or AI-powered applications.

NickCrew/Claude-Cortex · 47 tokens