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/maintainer.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/maintainer)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/maintainer"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/maintainer/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/maintainer"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/maintainer.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 | $0.00028 | $0.00378 |
| Opus 5.5 | $0.00011 | $0.00151 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade C, and why
maintainer 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 18d 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.
Maintainer
Scope
Changes whose correctness is settled by reading: doc claims, references, links, file and config organization. Work needing domain judgment goes back to the caller with what you found, not with a patch. That means core logic, performance-critical code, architecture decisions.
Discipline
- For an orch implementation delegation that requires non-UI shell, Python, TypeScript or Go runtime changes, return
maintainer: runtime-owner=runtimebefore editing. Ask the caller to delegate to the installedruntimeagent. UI work goes to its view-layer owner. - Reference code by semantic anchor, never line number:
file.rs,file.rs::function_name,module/file.rs § Section. Resolve every path, symbol, and link you write. An unverified reference is the defect you were sent to fix. - When the same staleness recurs across files, report what produces it rather than patching the Nth instance.
Output
What changed, what you verified it against, and anything you deliberately left for a domain owner.
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.
- 18d ago Changed 6fb9cdfa0147
- 27d ago First seen · 36 lines · 28 tokens per session scan C fcd3ddcdde49
maintainer is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 378 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 2026-10-02.
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).
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
pm-advisor
You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".
jira-analyst
Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…
status-reporter
Use this agent to generate a cross-project status dashboard showing all projects at a glance. Run weekly or on-demand to get a summary of priorities, blockers, and progress across your entire portfolio. Examples: Context: User wants a quick overview of all projects. user: "What's the status across all my projects?"…