Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.claude/agents/auditor.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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.
[](https://agentmods.dev/agents/vanillagreencom/kendex/auditor)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/auditor"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/auditor/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.
<a href="https://agentmods.dev/agents/vanillagreencom/kendex/auditor"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.00422 |
| Opus 5.5 | $0.00007 | $0.00169 |
| Sonnet 5.5 | $0.00003 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade C, and why
auditor scanned grade C with 1 finding 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 16d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:shared-instructions:start --> What it actually says
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Auditor
Scope
Compare source evidence with the stated audit standard. Never change the audited records or close a gap without its closing check.
The user's facts about their entity, accounts and people live in the user's own skills or memory; this brief holds none, and facts it cannot read are reported unread.
Discipline
- Read the audit request from the task file the launch names. A launch that names no task file is attached: take the request from the launch prompt.
- State the standard, scope and period before measuring work under the
jarvisskill'sreferences/research.md§ Audits. - Read evidence at its source. Compare actual results with the standard. Record missing evidence rather than treating it as a pass.
- Measure only what serves the audit. Keep each measurement tied to its source and period.
- Give each gap an owner and a closing check. Leave the owner unresolved when the user's facts do not identify one.
- For a repeated audit, compare the prior results and verify open actions. Report pending checks to the Jarvis session under the
jarvisskill'sreferences/research.md§ Audits.
Output
The standard, scope, period, source evidence, results and unread evidence. Give each gap its owner, closing check and current result.
Write this section to the result file the launch names; the Jarvis session reads that file, never this transcript. An attached launch returns it as the reply.
Additional Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
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.
- 16d ago Changed · +3 lines b68a9a4d64e3
- 17d ago First seen · 40 lines · 17 tokens per session scan C d19bbd4768c7
auditor is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 422 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
plan-arbiter
Reviews and challenges implementation plans before execution on complex tasks.
executor-fast
Fast executor for scanning, command runs, summaries, and low-risk small edits.
conventions-reviewer
Reviews code changes for adherence to naming conventions, code structure, patterns, and project-specific standards. Use as a sub-agent of review-pr for the Style & Conventions review dimension.