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/.agents/skills/deep-research/SKILL.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/skills/vanillagreencom/kendex/deep-research)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/deep-research"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/deep-research/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/skills/vanillagreencom/kendex/deep-research"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/deep-research.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 | $0.00021 | $0.01209 |
| Opus 5.5 | $0.00008 | $0.00484 |
| Sonnet 5.5 | $0.00004 | $0.00242 |
| Haiku 4.5 | $0.00002 | $0.00121 |
Grade C, and why
deep-research 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 21d 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:project-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
Problems with a kendex-owned skill go through kendex report; check ownership in the file first.
Deep Research
In Pi with the web_research tool active, use that tool, passing outputPath when creating a report. In every other harness, run scripts/deep-research with EXA_API_KEY set.
Rules
- Exa is the research source. Substitute a general web search only when Exa is unavailable and the user approves the fallback.
- Write
findings.mdto the path the caller requested, exactly. Given no path, write it totmp/plans/<slug>-research.md, never under a trackeddocs/path; the full rule isagents/planner.md§ Plan Artifacts. The report reaches other sessions as an attachment on its tracker issue. - Research on building against another system is held to code-quality § Over-Engineering.
- Cite sources for material claims. Provider payloads go in the sidecar JSON (
findings.raw.jsonbeside the report by default), never inline. Sanitize evidence excerpts: source-page headings must not render as headings. - Once the report and its sidecar exist, run
validateand stop. No local reproduction, benchmarks, tests, code inspection, or implementation unless the caller asked for it. - A missing
EXA_API_KEYfails with setup instructions. Set it on this package's Customize tab in the kendex app, or by hand in the project's private env file —.env.localunlessKENDEX_ENV_FILEnames another. The value may be a key or a 1Passwordop://vault/item/fieldreference when theopCLI is installed and signed in. - Every mode uses the same findings sections. Record mode and source counts in
## Research Metadata.
Running
.agents/skills/deep-research/scripts/deep-research report "question" --mode standard --output path/to/findings.md
.agents/skills/deep-research/scripts/deep-research report --query-file prompt.txt --context-glob 'context-*.md' --mode full --output findings.md
.agents/skills/deep-research/scripts/deep-research json "question" --output raw.json
.agents/skills/deep-research/scripts/deep-research validate findings.md findings.raw.json
.agents/skills/deep-research/scripts/deep-research doctor
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago Changed · -1 lines b8fe6e96cd02
- 23d ago Changed 5070dd1407fe
- 29d ago Changed · +2 lines 7196f2734290
- 1mo ago Changed 705d40fea8bc
- 1mo ago Changed 16cbe350b886
- 1mo ago Changed · +6 lines scan A → C 1e338f6a0128
- 2mo ago First seen · 76 lines · 21 tokens per session scan A 1e9681ca3990
deep-research is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 1,209 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 skills, from other repositories
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
claude-md-revision
Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.
gather-retrospectives
Gather retrospective feedback from past Pi sessions about a package, tool, or workflow. Use for historical retros and recurring friction, not assessment of only the current session.