agentmods.dev

kendex: Skill for Claude Code

.agents/skills/github/SKILL.md

github is a skill for Claude Code from vanillagreencom/kendex. It costs 23 tokens per session (3,383 once invoked), scanned C, original, MIT.

A command-line helper for working with GitHub pull requests, including their discussions, reviews, files, checks, and merge status.

In plain words
What is it for?
Use it to view pull requests, list unresolved threads, inspect comments and files, find pull requests ready to merge or failing checks, and create pull requests.
Why use it?
It gathers pull-request information in structured output and handles common review and continuous-integration queries consistently. This reduces manual navigation and incomplete thread checks.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is vanillagreencom/kendex's own configuration. It tells Claude Code how to work on kendex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kendex configures →

not rated 87repo +2 changed 10d ago C scan 23 tokens original MIT
View source ↗ vanillagreencom/kendex kendex.ai
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.agents/skills/github/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vanillagreencom/kendex

Made for: Claude Code.

Wrote 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.

agentmods badge for github

README.md
[![agentmods](https://agentmods.dev/badge/skills/vanillagreencom/kendex/github/github.svg)](https://agentmods.dev/skills/vanillagreencom/kendex/github)
Your own site
<a href="https://agentmods.dev/skills/vanillagreencom/kendex/github"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/github/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.

agentmods 80×15 button for github

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanillagreencom/kendex/github"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,383 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.03383
Opus 5.5 $0.00009 $0.01353
Sonnet 5.5 $0.00005 $0.00677
Haiku 4.5 $0.00002 $0.00338

Measured 10d ago against content hash 3a976a0ddff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

github 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 10d ago.

The scan reads SKILL.md. This mod also ships 39 executable files (scripts/commands/bot-token.sh, scripts/commands/check-review-replies.sh, scripts/commands/ci-classify-refusal.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 -->
.agents/skills/github/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 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.

GitHub pull requests

.agents/skills/github/scripts/github.sh [-C <path>] <command> [options]

Commands

Command Purpose
pr-data <N> [--actionable] Get PR with threads, comments, files. --actionable: unresolved non-outdated only.
pr-view [N] [--json FIELDS] View PR details (wraps gh pr view with bounded auth/no-PR errors)
pr-threads <N> [--unresolved|--resolved] [--format=safe|raw] Complete paginated thread list/count, outdated included. Both filters apply in both formats. See PR blocked with no visible conversations.
pr-timeline <N> [--repo OWNER/REPO] [--gate-context NAME] One PR's phase stamps, push and bot review times, CI spans, and review and fix rounds as one JSON object. Bot reviews exclude reply-only reviews. CI figures exclude Copilot review checks. --help defines the clean span over each workflow run's latest attempt and the read limits.
pr-list-ready [--all] [--format=safe|table] List PRs ready for merge
pr-list-failing [--all] [--format=safe|table] List PRs with CI failures
pr-create [--title T] [--body B | --body-file PATH] [--base B] [--draft] [--dry-run] [--force] Create PR as bot against --base, else the repository's default branch: WORKTREE_DEFAULT_BRANCH when set, else GitHub's. Safety checks: the head is not the base, has commits, pushed; --force skips them.
pr-edit-body <N> --body-file PATH Update an existing PR body through the sanitized router.
pr-merge <N> [--check|--auto] Merge PR. --check reports readiness as JSON on stdout plus a one-word verdict and head-run: <ids> (the run scope of the CI classification) on stderr; --auto queues a currently-blocked PR, and arms only where the base branch's rulesets require at least 1 approval and thread resolution and dismiss stale approvals on push, and refuses the admin route unless --queue explicitly requests a queue arm; the immediate merge passes --admin to GitHub only where the queue is all its token would bypass and the PR is not queue-only. Three exit codes. See PR Merge Outcomes.
ci-classify-refusal <N> Name the cause of a pr-merge refusal. Output and retry contract: ci-classify-refusal --help.
check-review-replies <N> Judge what the PR's review replies say, read live and read-only. See Review reply check.
pr-cross-check [N...] [--quick|--verify] Cross-PR analysis. --verify: full build+test (auto-detects build system).
pr-issue <N> [--format=safe|text] Extract issue ID from PR branch (configurable via GH_ISSUE_PATTERN)
label-add <PR-or-issue> <label> [--issue] [--required|--optional] Add a label after checking the live inventory. Mode semantics and exit codes: label-add --help.
label-remove <PR-or-issue> <label> [--issue] Remove a label through the sanitized router.
ci-logs <N> [--lines N] [--format=safe|text] Get CI failure logs for PR
bot-token [--format=safe|text] Check if bot token is configured, naming the selected variable as source
dismiss-review <PR> [--bot|--user NAME] [--message M] Dismiss blocking review. The exit status reports whether the dismissals landed: dismiss-review --help.
resolve-thread <PRRT_...> Mark thread(s) resolved. Works on threads the UI cannot render. The exit status reports whether the mutations landed: resolve-thread --help. See PR blocked with no visible conversations.
unresolve-thread <PRRT_...> Reopen thread(s). The exit status reports whether the mutations landed: unresolve-thread --help.
post-reply <PRRT_...|numeric-id> [body | --body-file PATH] [--pr N] Reply to review comment. --pr N is REQUIRED for numeric comment IDs; thread PRRT_... IDs need no PR number.
post-comment <PR> [body | --body-file PATH] Post PR-level comment.
find-comment <PR> --pattern <regex> Find comment by pattern/author
edit-comment <id> [body | --body-file PATH] Edit an existing comment, PR-level (#issuecomment-<id>) or inside a review thread (#discussion_r<id>). Endpoint order and the unknown-id refusal: edit-comment --help.
sticky-comment <PR> [--verdict|--analysis|--body] Get bot sticky comment. --verdict: quick pass/fail. --analysis: deep recommendation.

Read the full file on GitHub · 131 lines

Files

What ships with it

44 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.

Changes

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.

  1. 10d ago Changed 3a976a0ddff0
  2. 11d ago Changed · +8 lines · +1 tokens per session 307de9029b7f
  3. 15d ago Changed · +4 lines 9f0f91d59538
  4. 17d ago Changed d07f2dbbfa98
  5. 20d ago Changed 44119daead67
  6. 21d ago Changed · -1 lines bbe58f32057a
  7. 22d ago Changed eabf38bad130
  8. 23d ago Changed 27b43462f04e
  9. 25d ago Changed · +9 lines db6374b33d34
  10. 26d ago First seen · 111 lines · 22 tokens per session scan C afa88addbe74

Subscribe to this mod's changes

github is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 3,383 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.

Code reviewCommitsGit and workflowagent-managementagent-managerai-agentsintegrationpi-coding-agentpi-extensionpi-package
Related

Other skills, from other repositories

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.

mrclrchtr/supi · 7 tokens

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.

w-winter/dot314 · 44 tokens

committing-code

Create normal git commits with logical grouping. Use when committing, saving changes, creating commits, or grouping work into commits. For drafting or editing commit messages without committing, use writing-style. NOT for amending, rebasing, force-pushing, or rewriting history.

alexei-led/cc-thingz · 57 tokens

configuring-git-hygiene

Configure safe git workflow hygiene: pre-commit/pre-push hooks, Gitleaks secret scanning, .gitignore rules, local git config, and guardrails. Use when setting up git hooks, gitleaks/git leaks, staged pre-commit checks, pre-push validation, core.hooksPath, .gitignore, or git config best practices. NOT for creating…

alexei-led/cc-thingz · 111 tokens

github-pr

Automates the end-to-end Git workflow: branch creation, staging, committing, pushing, and opening or updating a GitHub pull request. Use when a feature or fix is ready for review and requires a structured PR, or when branch changes may need to be pushed to an existing PR for follow-up review.

mfmezger/ai_agent_dotfiles · 65 tokens

review-delta

Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

tirth8205/code-review-graph · 24 tokens