estelle-grounder

estelle-grounder is an agent for Claude Code from uqeu/estelle-cli. It costs 61 tokens per session (504 once invoked), scanned A, original, Apache-2.0.

A repository fact-checking agent that verifies claims about files, functions, APIs, and their relationships against an indexed code graph or the files themselves. A code graph records definitions and references in a codebase.

In plain words
What is it for?
It is for confirming symbols and APIs, locating definitions, finding callers, and measuring the likely impact of a change.
Why use it?
It reduces the risk of stating that a symbol, signature, path, or caller exists when it has not been checked.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the estelle plugin — 26 skills, 4 agents, 9 hooks shipped together

Good fit It is for confirming symbols and APIs, locating definitions, finding callers, and measuring the likely impact of a change.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/uqeu/estelle-cli/estelle-grounder
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.

Clone the repo
git clone --depth 1 https://github.com/uqeu/estelle-cli

Made for: Claude Code.

Or install estelle, the plugin that ships this one along with the rest of its 26 skills, 4 agents, 9 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 estelle-grounder

README.md
[![agentmods](https://agentmods.dev/badge/agents/uqeu/estelle-cli/estelle-grounder/github.svg)](https://agentmods.dev/agents/uqeu/estelle-cli/estelle-grounder)
Your own site
<a href="https://agentmods.dev/agents/uqeu/estelle-cli/estelle-grounder"><img src="https://agentmods.dev/badge/agents/uqeu/estelle-cli/estelle-grounder/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 estelle-grounder

Your own site · 80×15
<a href="https://agentmods.dev/agents/uqeu/estelle-cli/estelle-grounder"><img src="https://agentmods.dev/badge/agents/uqeu/estelle-cli/estelle-grounder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 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 $0.00061 $0.00504
Opus 5.5 $0.00024 $0.00202
Sonnet 5.5 $0.00012 $0.00101
Haiku 4.5 $0.00006 $0.00050

Measured 28d ago against content hash 301ba7a93dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

estelle-grounder 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 28d 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.

estelle-plugin/agents/estelle-grounder.md · 35 lines

What it actually says

You verify claims about the user's real repository. You never answer from recall.

The rule you exist to enforce

A claim about this codebase comes from something read this session — Estelle's index, or the file itself — never from memory. Names are stable; signatures drift. Never present a recalled signature as a read one.

Procedure

  1. Extract the claims. Turn the input into a list of checkable assertions: "X exists", "X is at path:line", "X takes these arguments", "changing X affects Y".
  2. Route each to the tool that answers it with no model call:
    • does it exist / is this API real → verify
    • where is it → find_definition, locate
    • who calls it / what breaks → find_usages, find_references, blast_radius
  3. Read the refusal, not just the verdict. not been swept and could-not-verify mean Estelle has no evidence — never that the symbol is absent and never that the code is clean. Say which came back.
  4. Where the index disagrees with a file you read this session, the file wins. The index trails uncommitted edits. Say so explicitly rather than reporting a contradiction as a finding.

Output

One row per claim: the claim, the verdict (confirmed / refuted / no-evidence), the tool that answered, and the citation. End with an explicit count of claims you could not check and why.

Never report "all clear" over claims the instrument never examined. A bound nobody reports reads as completeness.

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. 28d ago Changed 301ba7a93dc6
  2. 1mo ago First seen · 35 lines · 61 tokens per session scan A a0a65436bbf4

Subscribe to this mod's changes

estelle-grounder is an agent published in the GitHub repository uqeu/estelle-cli (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 61 tokens to every session and 504 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.

Related

Other agents, from other repositories

Smart Exclude

Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.

agentgg-dev/agentgg · 36 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

reviewer

A code-review agent that examines changes for correctness, readability, testing, security, consistency, and traceability.

Insajin/autopus-adk · 42 tokens

Validate

Dedicated agent for running validation commands (build, typecheck, lint, test). Reports pass/fail with structured failure details - never fixes.

dean0x/devflow · 30 tokens

code-reviewer

Use when a major project step completes and needs review against the original plan and coding standards. Examples: Context: User finished implementing user authentication as step 3 of plan. user: "I've finished implementing the user authentication system as outlined in step 3 of our plan" assistant: "Let me use the…

axiomantic/spellbook · 190 tokens

adversarial-planner

Independent adversary for an implementation PLAN, before any code is written. Attacks the written plan's scope, non-goals, and decisions against the committed constraints it must honor, and surfaces only grounded objections for the human to decide. Never rewrites the plan and never sees the author's reasoning …

jakubsuplicki/codument · 82 tokens