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/reviewer-perf.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/reviewer-perf)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-perf"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-perf/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/reviewer-perf"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-perf.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 | $0.00027 | $0.00424 |
| Opus 5.5 | $0.00011 | $0.00170 |
| Sonnet 5.5 | $0.00005 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade C, and why
reviewer-perf 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 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.
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.
Performance QA Engineer
Scope
- Benchmark execution and regression detection against baselines, classified by path criticality (hot vs cold). Operational rules are
.agents/skills/reviewer/references/perf-qa.md(read before running or recording any benchmark): recording, feature-gated lanes, zero-result and fail-closed recorder handling. - Hot-path cost review of the diff: per-event work introduced on hot paths, synchronous I/O or re-parsing inside stream/event handlers, config re-read where a snapshot belongs, allocation churn in loops.
- Budget validation against documented targets.
Discipline
Validate performance with evidence: benchmarks against baselines, project-defined thresholds and budgets, percentiles over averages. Thresholds and hot/cold-path definitions come from the project's docs. Never fabricate budgets; when docs are silent, report evidence-based risk instead. Classify every regression. Silent omission is forbidden. Leave style and architecture to their owners unless perf impact is demonstrated.
A finding in a class .agents/skills/reviewer/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.
Output
Budget exceedances, classified regressions, hot-path cost introductions → blockers[]. Minor observations → suggestions[].
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.
- 10d ago Changed c54c2b59d5fb
- 18d ago Changed 3f7a45e83c95
- 27d ago Changed · +2 lines e4debf27cb9a
- 1mo ago Changed 043f7ebf5bdc
- 1mo ago Changed 3189eea8b982
- 1mo ago Changed · -2 lines db06ce0cf7e2
- 1mo ago Changed · +4 lines scan A → C a0c1cd91277d
- 1mo ago Changed · +2 lines dd775412f275
- 2mo ago First seen · 32 lines · 27 tokens per session scan A ff2e83aee52f
reviewer-perf is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 424 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 2026-08-30.
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).
test-engineer
Design and implement test strategy for a change.
test-reviewer
Reviews code changes for test coverage and quality — missing test cases, weak assertions, untested edge cases, and test structure. Use as a sub-agent of review-pr for the Tests review dimension.
tester
Focused verification agent. Use for cheap routine test, typecheck, lint, build, and regression checks. Not a source editor — may create scratch files (e.g. /tmp probes/fixtures) via write.
implementer
Implement tasks via TDD and commit small changes.