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 plan-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/plan-guide)<a href="https://agentmods.dev/skills/xonovex/platform/plan-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/plan-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/plan-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/plan-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 | $0.00107 | $0.01419 |
| Opus 5.5 | $0.00043 | $0.00568 |
| Sonnet 5.5 | $0.00021 | $0.00284 |
| Haiku 4.5 | $0.00011 | $0.00142 |
Grade A, and why
plan-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 7d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Planning Guidelines
Provide implementation-planning procedures selected by a caller. This skill owns planning behavior and planning-oriented research, not general code-quality audits, invocation, lifecycle governance, or persistence.
Core Principles
- Explicit subjects: accept an inline plan or an opaque provider-native reference plus an optional native revision
- Provider-owned references: let a selected provider resolve, version, or relate native resources; return operation results inline
- Research first: ground plans in codebase evidence, constraints, uncertainty, and relevant external sources
- Read-only analysis: planning research, critique, and validation report findings without changing their subjects; only continuation implements planned work
- Skills to consult: plans name applicable implementation capabilities, and continuation loads them before editing
- Evidence-based validation: check explicit success criteria and Definition of Done evidence, not merely command exit codes
Operation boundaries, effect modes, handoff shape, decision anchors, and authority belong to the caller; this skill adds no rule of its own on any of them.
Planning Operations
- Research: investigate codebase and external evidence for a future plan, see references/research.md
- Create: author one high-level plan and stop before detailed subplans, see references/create.md
- Critique: independently stress-test one plan without revising it, see references/critique.md
- Revise: apply explicit feedback to a new plan revision, see references/revise.md
- Expand: derive focused child plans and their execution ordering, see references/expand.md
- Continue: implement one plan or child plan and stop, see references/continue.md
- Update: refresh descriptive progress and validation evidence, see references/update.md
- Validate: evaluate explicit success criteria without changing the plan, see references/validate.md
- Followup: close out a completed, paused, or handed-over plan with an inline follow-up record, see references/followup.md
- Distill: turn a completed plan's implementation into a replayable skill suite, see references/distill.md
What ships with it
22 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.
- CHANGELOG.md 879 B
- eval-queries.json 5.8 KB
- evals.json 14 KB
- moon.yml 166 B
- references/accept.md 1.3 KB
- references/continue.md 3.7 KB
- references/create.md 2.8 KB
- references/critique.md 2.7 KB
- references/decide.md 4.9 KB
- references/delegate.md 6.5 KB
- references/distill-sources.md 3.7 KB
- references/distill-templates.md 3.2 KB
- references/distill.md 4.2 KB
- references/expand.md 2.5 KB
- references/followup-templates.md 3.8 KB
- references/followup.md 3.6 KB
- references/reject.md 1.2 KB
- references/research.md 2.8 KB
- references/revise.md 2.3 KB
- references/update.md 1.8 KB
- references/validate.md 2.4 KB
- SOURCES.md 601 B
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.
- 7d ago Changed · -3 lines ca6750001fdb
- 1mo ago First seen · 75 lines · 107 tokens per session scan A d2af4705b196
plan-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 5d ago), licensed MIT. It adds 107 tokens to every session and 1,419 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.