agentmods.dev

kendex: Skill for Claude Code

.agents/skills/bot-instructions/SKILL.md

bot-instructions is a skill for Claude Code from vanillagreencom/kendex. It costs 31 tokens per session (3,928 once invoked), scanned C, original, MIT.

A skill for creating, checking, or adopting instruction files used by automated code-review bots. It maps each bot to the files and rules it reads and provides commands for rendering and validation.

In plain words
What is it for?
Use it to render bot instructions, validate them, or adopt existing hand-written files for GitHub review bots and other code-review services.
Why use it?
It keeps review-bot guidance consistent across tools and helps detect when generated instruction files no longer match the shared rules.

Skill for Claude Code

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

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 31 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/bot-instructions/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 bot-instructions

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/vanillagreencom/kendex/bot-instructions"><img src="https://agentmods.dev/badge/skills/vanillagreencom/kendex/bot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,928 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 $0.00031 $0.03928
Opus 5.5 $0.00012 $0.01571
Sonnet 5.5 $0.00006 $0.00786
Haiku 4.5 $0.00003 $0.00393

Measured 10d ago against content hash 29900f7b5389, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

bot-instructions 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 26 executable files (scripts/lib/__init__.py, scripts/lib/cli.py, scripts/lib/config.py, …), 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/bot-instructions/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 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.

Bot Instructions

.agents/skills/bot-instructions/scripts/bot-instructions render   # write every enabled surface
.agents/skills/bot-instructions/scripts/bot-instructions check    # re-render and compare
.agents/skills/bot-instructions/scripts/bot-instructions adopt    # take hand-written files over
.agents/skills/bot-instructions/scripts/bot-instructions retire   # revoke kendex automatic rendering on removal

Flags: --repo, --spec, --staged, --output full|local, --dry-run; bot-instructions --help. Python 3.11+.

--output local limits render, check and adopt to the AGENTS.md review region. The doctrine loader selects SKILL.md or SKILL.md.disabled. The pointer uses that filename and the #doctrine anchor inside the selected checkout installation. Checkout parent paths resolve through their symlinks. The installation's own symlink keeps its checkout path. Source reads use its canonical target. An external --spec needs a matching selected installation inside the checkout. Otherwise local mode refuses: use --output full or install the package inside the checkout. Remote files are excluded from validation, adoption, writes, orphan removal and ownership reports. Local review reads the package doctrine directly; repository doctrine overrides remain in the full render. The default --output full keeps every enabled bot output. adopt --dry-run reports the content to take over and its divergence, writes no marker, and refuses symlinked targets.

Exit codes: 0 clean, 1 findings, 2 could not complete. An unconfigured repository follows schemas/validators.md § orphan, including its empty JSON ownership report. The commit-guards chain runs check --staged itself where this package is installed. A pre-commit lane blocks on nonzero codes, except an older check's unconfigured refusal carrying its renders=none attestation.

Read the full file on GitHub · 168 lines

Files

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.

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 · +5 lines 29900f7b5389
  2. 14d ago Changed 54e39baec687
  3. 16d ago Changed 9994c6dc9d72
  4. 20d ago Changed · +1 lines 2b78fe9bc7e6
  5. 21d ago Changed · -1 lines 41c4096d5409
  6. 22d ago Changed 7629c4d0d5d0
  7. 23d ago Changed be3b6a253785
  8. 27d ago Changed · -10 lines 442ba979e505
  9. 28d ago Changed ef7d4d74b961
  10. 29d ago First seen · 173 lines · 31 tokens per session scan C 3dbf187e7026

Subscribe to this mod's changes

bot-instructions is a skill published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 3,928 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 2026-09-02.

Code reviewagent-managementagent-managerai-agentspi-coding-agentpi-extensionpi-packagereview
Related

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…

w-winter/dot314 · 84 tokens

text-search

Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.

w-winter/dot314 · 22 tokens

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.

mrclrchtr/supi · 39 tokens

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.

mrclrchtr/supi · 45 tokens

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.

mrclrchtr/supi · 38 tokens

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