Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/vanillagreencom/kendex/review-gatenpx skills add vanillagreencom/kendex --skill review-gategit 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/review-gate)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/review-gate"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/review-gate.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 | $0.00026 | $0.01783 |
| Opus 5 | $0.00013 | $0.00892 |
| Sonnet 5 | $0.00005 | $0.00357 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade C, and why
review-gate 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 yesterday.
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 — 158 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.
Review Gate
The gate answers ONE question: has this exact PR head been reviewed? It posts that answer as a commit status the repo's branch rules require. It does not check CI, re-run anything, or reason about jobs.
Two greens do NOT mean a review happened. Under REVIEW_GATE_MODE = "off"
the predicate evaluates no evidence and attests only that the repo disabled
the gate; and merge-group statuses never read the mode, posting green as
"merge-queue entry: post-approval by construction". Both:
references/settings.md § REVIEW_GATE_MODE.
Decision table
| Verdict | Status | Meaning |
|---|---|---|
approved |
success |
Evidence exists for this head; no standing objection; no unresolved threads. Under REVIEW_GATE_MODE = "off" the predicate evaluates NO term. Success there means only "gate disabled", stated in the status description. |
awaiting |
pending |
No review evidence for this head yet. |
threads-open |
pending |
Evidence exists, but review threads are unresolved. |
changes-requested |
failure |
A reviewer objects. Red means objection, never a build failure. |
untracked-claim |
failure |
A disposition reply that claims tracking and names no issue fails the gate. |
unreasoned-decline |
failure |
A decline whose reason strips to nothing against the label vocabulary fails the gate. |
| (exit 2, no verdict) | unchanged | A read failed or config is invalid. Take NO action; retry next pass. |
Pending text names the head; which sources open the gate is
references/settings.md § Reading the pending status.
How the two failure verdicts parse a reply is DEVELOPMENT.md § Tracking-claim
parsing and § Decline parsing; what to write instead is orch's
references/finding-disposition.md.
What ships with it
34 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.
- DEVELOPMENT.md 15 KB
- kendex.settings.toml.example 5.4 KB
- README.md 4.4 KB
- references/adoption.md 14 KB
- references/settings.md 12 KB
- references/vendored-paths.md 13 KB
- scripts/lib/settings.sh 15 KB runs code
- scripts/pr-watch.sh 43 KB runs code
- scripts/review-predicate-selftest.sh 117 KB runs code
- scripts/review-predicate.sh 87 KB runs code
- scripts/review-writer.sh 14 KB runs code
- scripts/validate-workflow.sh 17 KB runs code
- scripts/validate.sh 27 KB runs code
- templates/review-gate-writer.yml 38 KB
- templates/vendored-paths.instructions.md 7.8 KB
- tests/corpus/declines-known-limit.txt 5.4 KB
- tests/corpus/declines-reasoned.txt 5.9 KB
- tests/corpus/declines-unreasoned.txt 15 KB
- tests/lib/gh-shim.sh 4.5 KB runs code
- tests/lib/sandbox.sh 5.1 KB runs code
- tests/lib/selftest-fixtures.sh 3.6 KB runs code
- tests/pr-watch-help.test.sh 2.1 KB runs code
- tests/pr-watch.test.sh 51 KB runs code
- tests/predicate-re2-engine.test.sh 12 KB runs code
- tests/predicate-unknown-arg.test.sh 6.3 KB runs code
- tests/review-writer-template.test.sh 36 KB runs code
- tests/review-writer.test.sh 31 KB runs code
- tests/settings-parsing.test.sh 26 KB runs code
- tests/settings-vars-documented.test.sh 4.8 KB runs code
- tests/unreasoned-decline.test.sh 38 KB runs code
- tests/validate-workflow.test.sh 17 KB runs code
- tests/validate.test.sh 20 KB runs code
- tests/vendored-class.test.sh 8.8 KB runs code
- tests/vendored-paths-template.test.sh 8.1 KB runs code
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.
- yesterday Changed · +9 lines scan A → C 62746e2eac49
- 2d ago Changed · -138 lines 1e13a98e097e
- 5d ago First seen · 287 lines · 26 tokens per session scan A 2c24c8f88ad6
review-gate is a skill published in the GitHub repository vanillagreencom/kendex (66 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 1,783 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 -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.
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.