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/review-gate/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/review-gate)<a href="https://agentmods.dev/skills/vanillagreencom/kendex/review-gate"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/review-gate/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/review-gate"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/review-gate.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 | $0.00015 | $0.01290 |
| Opus 5.5 | $0.00006 | $0.00516 |
| Sonnet 5.5 | $0.00003 | $0.00258 |
| Haiku 4.5 | $0.00002 | $0.00129 |
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 8d 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 — 66 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 operations
GitHub rulesets enforce approvals, stale-approval dismissal and review-thread resolution. This package reports repository configuration and refreshes consumer installs. It posts no review status. When the github skill is installed, its scripts/pr-watch.sh is the pull-request watcher.
Organization standard
Run scripts/validate-standard.sh for a read-only report. The organization's own tooling sets up the review-secret environment and the app installation. Settings and repository wiring: references/adoption.md.
Consumer refresh
An existing consumer first follows references/adoption.md § Trusted removal for an existing consumer. Automatic refresh runs only after that normally reviewed removal merges. Fresh installs run refresh/adopt-refresh.sh from a kendex checkout at a release tag. Each consumer calls the shared workflow, which runs its scripts from that release checkout. Environment and token requirements: references/adoption.md § Automatic consumer refresh.
Consumers refresh on a schedule or a manual run. An organization managed by fleet uses fleet repos kendex-refresh for immediate refresh dispatch. Dispatch requirements: references/adoption.md § Immediate refresh.
4. Operations
A pull request with no automatic review needs a Copilot request. When orch is present, request through its mode owner, approval-wait <PR#> --request-review --base-checkout PATH, per orch's references/gates.md § Copilot requests, which routes its off and fallback answers. Without orch, request directly: gh pr edit <PR#> --add-reviewer @copilot. Ruleset targeting and request failures, when the github skill is installed: its references/automatic-review.md. The central request workflow: references/adoption.md § Central Copilot request workflow.
What ships with it
16 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.
- kendex.settings.toml.example 1.4 KB
- README.md 1.3 KB
- references/adoption.md 34 KB
- references/vendored-paths.md 8.8 KB
- retired-settings.json 2.7 KB
- scripts/install-latest.sh 4.1 KB runs code
- scripts/lib/arm-published-head.sh 1.6 KB runs code
- scripts/lib/diagnostics.sh 701 B runs code
- scripts/lib/environment.py 6.9 KB runs code
- scripts/lib/settings.sh 19 KB runs code
- scripts/lib/standard.sh 4.1 KB runs code
- scripts/validate-standard.sh 30 KB runs code
- standard.json 58 B
- templates/kendex-refresh.yml 3.6 KB
- templates/review-gate-writer.yml 42 KB
- templates/vendored-paths.instructions.md 7.7 KB
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.
- 8d ago Changed · -1 lines ef533f6905f1
- 11d ago Changed · +4 lines · -5 tokens per session 4f89ccbdecbb
- 17d ago Changed 85666252a6e9
- 18d ago Changed 524aeb43ac78
- 19d ago Changed · +1 lines c1c659935739
- 20d ago Changed af2abb45e669
- 21d ago Changed · -1 lines 3b1f9f9090c0
- 22d ago Changed ca4216ffef48
- 23d ago Changed 6e6a835b20e4
- 24d ago First seen · 63 lines · 20 tokens per session scan C d6b2d747c7b2
review-gate is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,290 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.
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.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.