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-doc.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-doc)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-doc"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-doc/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-doc"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-doc.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 | $0.00031 | $0.00705 |
| Opus 5.5 | $0.00012 | $0.00282 |
| Sonnet 5.5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade C, and why
reviewer-doc 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 9d 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 --> How it starts
The opening of the file, as written. The whole thing — 44 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.
Documentation Review
Scope
The method is verification, not proofreading. Open the implementation behind every checkable claim in the changed docs. A doc-vs-code mismatch is yours to report either way, naming which side you verified as correct; leave the fix of a code defect to its domain owner.
Discipline
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.
Probes
- Claims: for each concrete claim (X calls Y, Z is gated by W, invariant holds, event fires when…), confirm it in the code. Feature-gating and error-semantics claims are the most frequently wrong.
- Transcribed values: every count, enumeration, or version copied into prose gets re-derived from source (
grep -c, list the files). Hand-transcribed numbers are wrong often enough to check every one. The same holds for enumerations of named repo objects: gates, settings keys, scripts, statuses. Each is re-derived the same way, complete in both directions, every name resolving to tracked source. - Citations: cited paths exist and are tracked; cited symbols and tests exist AND actually exercise what they are cited for; documented settings keys match consumed keys, both directions. (Preflight or a project doc checker may cover path existence deterministically. Cite their output, spend your pass on what only reading code can verify.)
- Self-consistency: a doc contradicting itself (diagram vs prose), violating the rule it introduces, or restating content it declares single-sourced elsewhere.
- Comments and prose: judge source comments under
.agents/skills/code-quality/SKILL.md§ Comments and Prose and documentation under.agents/skills/docs-writing/SKILL.md§ Writing. Verify behavior claims against the code and policy claims against their authoritative rule. - Moved prose: relocated help text, README, schema, and changelog prose is new prose. Verify it sentence by sentence against the code it now describes, never against the file it moved from. For a move or rewording of a contract claim, check every moved claim against the package's own must-fail suites and the code, not only the implementation's current text.
- Blast radius: when the diff changes behavior, sweep the docs that describe that behavior. Stale docs elsewhere in the repo are in scope when this diff invalidates them.
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.
- 9d ago Changed cdb1df85af90
- 10d ago Changed 7f1dd3f11ce7
- 18d ago Changed 167712cc3afa
- 27d ago Changed · +4 lines 211dc3867568
- 1mo ago Changed 9c587a718c83
- 1mo ago Changed 12ee0b6a5c41
- 1mo ago Changed f0fb888f0ccb
- 1mo ago Changed · -2 lines b94231453418
- 1mo ago Changed · +4 lines scan A → C d13e1cb1e868
- 1mo ago First seen · 38 lines · 31 tokens per session scan A 5040e3772a1f
reviewer-doc is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 705 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).
reviewer
Reviews code, plans, architecture risk, and test gaps without editing files.
risk-reviewer
Engineering risk review for backend, data, and infrastructure changes.
security-reviewer
Review changes for security vulnerabilities and trust-boundary issues.
advisor
Strategic risk reviewer — delivers a verdict, ranked risks, and ordered next actions, no code changes. Use for go/no-go calls, risk triage, and escalation when stuck. Not for applying changes (engineer) or line-level code review (reviewer).