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 skills add xonovex/platform --skill instruction-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/instruction-guide)<a href="https://agentmods.dev/skills/xonovex/platform/instruction-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/instruction-guide/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/xonovex/platform/instruction-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/instruction-guide.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 | $0.00094 | $0.00782 |
| Opus 5.5 | $0.00038 | $0.00313 |
| Sonnet 5.5 | $0.00019 | $0.00156 |
| Haiku 4.5 | $0.00009 | $0.00078 |
Grade A, and why
instruction-guide scanned grade A with 0 findings 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 1mo 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instruction Guidelines
Author, refresh, simplify, consolidate, and port AGENTS.md project-instruction files while preserving technology names, paths, and project context.
Core Principles
- Open standard: AGENTS.md is the cross-harness format read by many agent harnesses; keep content harness-neutral
- README for agents: operational detail (commands, conventions, gotchas) belongs in AGENTS.md; human-onboarding prose belongs in README.md
- Teammate heuristic: "anything you'd tell a new teammate" belongs here; anything you'd tell a casual visitor belongs in README
- Nested precedence: for monorepos, the AGENTS.md closest to the edited file wins; place subproject-specific guidance in subdirectories
- Commands are executable: agents auto-run programmatic checks listed in AGENTS.md; treat command examples as instructions, not just docs
- Advisory scope: AGENTS.md communicates project guidance; it does not itself execute automation
- Preserve Project Context: never modify technology names, paths, or commands
- Match Style and Voice: maintain the target file's formatting and terminology
- Structure Integrity: keep section order and hierarchy intact; preview changes (dry-run) before applying
- Signal Over Volume: keep only non-obvious content; anything inferable from
package.json+ source belongs in the code, not the doc - Deletion-first editing: a simplify or consolidate pass cuts at least as much as it adds, and reuses existing vocabulary rather than coining new terms; skill-guide owns this rule
- Living documentation: update alongside project changes (sync operation)
Gotchas
- AGENTS.md files that restate code are worse than no doc. They rot when the code changes
- Tech names look like noise but are essential; never substitute generics for
moon/Terraform/npm - Root AGENTS.md is the project entry-point doc, never auto-delete even if it looks thin
- Manual descriptions in Subdirectories often encode info the filesystem can't (purpose, owner, status): preserve verbatim during sync
- Nested AGENTS.md aren't duplicates. They're scope-specific overrides; never merge a subproject's file into the root
- Build / test commands listed in AGENTS.md will be executed by agents; broken commands waste agent turns
- "Always do X" in AGENTS.md enforces nothing. The model may not comply and may never load the file; capitalizing MUST adds no executor, and the failure is silent because the rule never ran
What ships with it
9 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.
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.
- 1mo ago First seen · 42 lines · 94 tokens per session scan A 8b5502377202
instruction-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 782 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-08.
Other skills, from other repositories
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
docker
Use when authoring or auditing a Dockerfile, shrinking a bloated image, hardening a container that runs as root, picking a base image, or wiring a Compose dev loop with hot reload. NOT CI builds or deploy-to-host (that is deployment), NOT k8s autoscaling (that is scaling), NOT app-level injection or secrets-in-code…
kastell
Server security auditing, hardening, and fleet management. 457 security checks across 30 categories (SSH, Firewall, Docker, TLS, HTTP Headers), CIS/PCI-DSS/HIPAA compliance mapping, 24-step production hardening, and 13 MCP tools. Supports Hetzner, DigitalOcean, Vultr, and Linode with Coolify, Dokploy, and bare VPS…
ilo
Run builds, tests, and other tooling inside a reproducible, containerized dev environment via the ilo CLI instead of on the host. Use this whenever a project relies on ilo, devcontainers, or container-based build environments — it has a .ilo.rc / .ilo/ilo.rc, dev/ argument files, a Containerfile/Dockerfile, a…
docker-compose-local-setup
Creates or updates local multi-service orchestration using docker compose. Covers compose.yaml design, service health checks, dependson readiness, env files, named volumes, migrations/seeds jobs, verification commands, and cleanup workflows for local development.
compose
A guide to Docker Compose, a tool for defining and running applications made of multiple containers, such as a web app, API, and database.