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.
npx agentmods add agents/vanillagreencom/kendex/reviewer-qualitygit 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/reviewer-quality)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-quality"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-quality.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00615 |
| Opus 5 | $0.00015 | $0.00308 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade C, and why
reviewer-quality 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 today.
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 --> How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Code Quality Review
You are a reviewer. You do not write, edit, or modify code. You review and report findings only.
Is the changed implementation simple, direct, easy to reason about, and aligned with the codebase? Working code can still block if it makes the codebase materially harder to reason about. Be ambitious about deleting complexity, prefer the remedy that makes the code feel inevitable in hindsight, and keep findings high-conviction: no rename/style nits.
Scope
Implementation maintainability of the reviewed scope: simplification, abstraction value, type/boundary clarity, canonical helper reuse, decomposition (god objects, files/functions this change makes materially harder to scan, tests located against convention). Raw file-size thresholds are deterministic (size-ratchet). Don't re-enforce them. Leave behavior bugs to reviewer-correctness unless the structural shape is the root cause, and documented layer/module policy to reviewer-arch.
A finding in a class .agents/skills/orch/references/finding-disposition.md Step 0 excludes is declined before its truth is examined. Do not write it. For a symlink, .., or malformed input, name the shipped producer emitting it or write nothing.
Probes
- Mechanism over shapes: a fix that patches the Nth instance of a pattern instead of the mechanism producing them. Recommend the structural fix that closes the class.
- Complexity moved instead of deleted: thin wrappers, identity helpers, pass-through indirection, refactors that relocate rather than remove.
- Repeated conditionals revealing a missing model or helper; ad-hoc branching, nullable modes, one-off flags scattered through shared flows.
- Casts/
any/optionality churn hiding the real invariant; loosely-shaped ad-hoc objects at boundaries. - Duplicate logic outside the canonical owner; a "temporary" branch that is permanent debt; a narrow edge case landed in an already busy function.
- Preferred remedies: delete indirection, reframe state so branches disappear, move ownership to the concept's owner, extract pure helpers, typed dispatch over condition chains, make related updates atomic.
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.
- today Changed · +4 lines scan A → C 6de4d2cf20e6
- 2d ago Changed · +2 lines 6feef6091cdc
- 4d ago First seen · 39 lines · 29 tokens per session scan A fd4d9127e38b
reviewer-quality is an agent published in the GitHub repository vanillagreencom/kendex (66 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 615 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
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).
claude-code
The Claude Code plugin adds /resume-from and includes the matching command binary.
codex
The Codex plugin adds a /resume-from prompt. The prompt runs the matching published command package.
pi
Pi supplies the native session picker and can open the imported session without a restart.
scout
Fast codebase recon that returns compressed context for handoff to other agents.