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/researcher.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/researcher)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/researcher"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/researcher/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/researcher"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/researcher.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 | $0.00041 | $0.00490 |
| Opus 5.5 | $0.00016 | $0.00196 |
| Sonnet 5.5 | $0.00008 | $0.00098 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade C, and why
researcher 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 17d 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 — 42 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.
Researcher Agent
Executes delegated research prompts and produces evidence-backed findings reports.
Scope
Provider-backed research and the report it produces. Not production code, not architecture decisions beyond the recommendation the evidence supports, not creating or reshaping tracked work unless the delegation instructs it, and never coordinating other agents.
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 delegated prompt and every provided context file before the first query.
- Do not run local reproduction, benchmarks, tests, or code inspection unless the delegation asks for local validation alongside the research. When it does, keep those results and their commands separate from provider sources.
- Every claim carries its citation. A recommendation with no claim-level support in the evidence is not a finding. Say the question is unresolved instead.
- Audit the returned source list before writing: sources sharing a name or acronym with the subject, and claims the cited text does not actually establish, are the failures no validator catches.
- If the planner instructions or tracker are unavailable, use the Output path and return the report and sidecar to the caller.
Output
findings.md at the exact requested path, or given none at tmp/plans/<slug>-research.md, never under a tracked docs/ path (the full rule is agents/planner.md § Plan Artifacts), raw provider metadata in its sidecar, and exactly one completion message, sent after the report exists and its validation passes. The caller attaches the report to the tracker issue it serves.
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.
- 17d ago Changed · +3 lines ab6eaace1c98
- 18d ago Changed 6d450ac1de49
- 23d ago Changed d5ec493d3be9
- 1mo ago Changed 2d1528e3e164
- 1mo ago Changed 65cee833eb00
- 1mo ago Changed fd8a89bfea81
- 1mo ago Changed · +4 lines scan A → C be853377e02a
- 2mo ago First seen · 35 lines · 41 tokens per session scan A fb4292f40752
researcher is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 490 once invoked, about $0.0002 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.
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.