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/dep-radar/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/dep-radar)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/dep-radar"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/dep-radar.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 5.1 | $0.00013 | $0.01655 |
| Opus 5 | $0.00006 | $0.00827 |
| Sonnet 5 | $0.00003 | $0.00331 |
| Haiku 4.5 | $0.00001 | $0.00166 |
Grade C, and why
dep-radar 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 2d 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 — 99 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.
dep-radar
inventory → detect → research → classify → upgrade-with-fixes → report the owner tier.
Generic engine only: concrete package names, pinned binaries, and fork lists live in the per-repo inventory, never here.
Load github before Phase 4 (PR creation, CI status, merges). Load worktree when a run applies more than one surface, one working copy per surface branch.
Operating policy (the contract with the product owner)
Rule keys are the contract; an inventory owner-rule cites them. Dropping or renaming a key changes the contract.
| Rule | Contract |
|---|---|
auto-with-fixes |
The default. Security fixes; patch/minor bumps; pinned-binary version+SHA refreshes from OFFICIAL manifests only; SDK, agent-tooling, and runtime-binary bumps and npm/cargo majors, doing the bump AND fixing its fallout (API migrations, re-vendored bundled-extension bridges, tests, CI) in the SAME per-surface workstream; bundled-extension fork updates and local patch rebases when the consuming repo's full test suite gates the sync. |
report-never-auto |
Model-weight swaps; changes to durable/recorded data scope; anything an inventory owner-rule explicitly demotes. Nothing else is report-by-default. |
uncertain |
Attempt the upgrade; report only what actually failed, with error output. |
defer |
Only on a strong concrete blocker you actually hit, such as a dropped capability with no migration path or a transitive that does not support the new version. Never a generic "it's a major" risk or any other anticipated one. |
one-pr-per-surface |
One PR per surface; never batch surfaces. A surface's fallout fixes go in THAT surface's PR. |
upstream-check-required |
Every pinned surface must have a wired upstream check command; a surface lacking one is an inventory defect the run must fix. |
dated-report |
Every run ends with a dated report. |
demote-only |
Inventory owner-rules may demote auto→report, never promote report→auto. |
What ships with it
1 file 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.
- 2d ago Changed · -29 lines a214cb8e35ec
- 3d ago Changed · +1 lines scan A → C b3f41d0013c4
- 5d ago Changed 95ffafda49a5
- 7d ago First seen · 127 lines · 13 tokens per session scan A eab72bfc5726
dep-radar is a skill published in the GitHub repository vanillagreencom/kendex (75 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 1,655 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 skills, from other repositories
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
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.
repoprompt-tool-guidance-refresh
Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses /.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool…
xcodebuildmcp
Build/test Xcode projects via the XcodeBuildMCP MCP server using a local CLI wrapper for pi (no MCP support). Use when the user mentions Xcode, xcodebuild, iOS builds/tests, or XcodeBuildMCP.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.