prism-onboard

prism-onboard is a skill for Claude Code, Codex from Shailesh200/prism. It costs 68 tokens per session (488 once invoked), scanned A, original, MIT.

A repository-orientation method for understanding an unfamiliar codebase before answering questions or making changes.

In plain words
What is it for?
Use it to learn a project's languages, frameworks, structure, packages, important code areas, and general health.
Why use it?
It reduces incorrect conclusions caused by inspecting only the files that happen to be open.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to learn a project's languages, frameworks, structure, packages, important code areas, and general health.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shailesh200/prism/prism-onboard
Install

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.

Any agent
npx skills add Shailesh200/prism --skill prism-onboard
Clone the repo
git clone --depth 1 https://github.com/Shailesh200/prism

Made for: Claude Code, Codex.

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 prism-onboard

README.md
[![agentmods](https://agentmods.dev/badge/skills/shailesh200/prism/prism-onboard/github.svg)](https://agentmods.dev/skills/shailesh200/prism/prism-onboard)
Your own site
<a href="https://agentmods.dev/skills/shailesh200/prism/prism-onboard"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-onboard/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 prism-onboard

Your own site · 80×15
<a href="https://agentmods.dev/skills/shailesh200/prism/prism-onboard"><img src="https://agentmods.dev/badge/skills/shailesh200/prism/prism-onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00068 $0.00488
Opus 5 $0.00034 $0.00244
Sonnet 5 $0.00014 $0.00098
Haiku 4.5 $0.00007 $0.00049

Measured 3d ago against content hash be69b333dea8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prism-onboard 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 3d 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.

packages/plugin/skills/prism-onboard/SKILL.md · 51 lines

What it actually says

Get your bearings first

Answering a structural question from the two or three files that happen to be open produces confident, wrong answers. The files an agent opens first are not a sample of the repository; they are a sample of what the user was last looking at.

The procedure

1. repository_dna. One call, and the fastest way to know what this project is: languages, frameworks, size, how it is organised. Start here on any repo you have not seen this session.

2. Then follow the question.

  • Layout and architecture → repository_map
  • Monorepo, or you saw multiple packages → list_packages
  • Where the important code lives → landmarks
  • Frameworks and versions in detail → stack_profile
  • What this directory is for → explain_area
  • Product surfaces rather than folders → list_features, feature_graph
  • General health, before proposing changes → repository_health

Two or three calls is usually enough. The point is to stop guessing, not to inventory everything before answering.

3. Answer in your own words. Summarise what you found. Do not paste tool output at the user — they asked a question, not for a report.

When the question is about a symbol, not the repository

Skip straight to find_symbol or search_symbols, then find_references. Orientation is for structural questions; a specific lookup does not need it.

Before you edit anything here

Orientation tells you where things are. It does not tell you what breaks if you change them — use blast_radius for that, per the prism-safe-change skill.

Note on timing

The first intelligence call in a session builds the index and can take a few seconds on a large repository. That is once, not per call. If you see PRISM_INDEX_REQUIRED, wait briefly and retry rather than falling back to reading files at random.

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. 3d ago First seen · 51 lines · 68 tokens per session scan A be69b333dea8

Subscribe to this mod's changes

prism-onboard is a skill published in the GitHub repository Shailesh200/prism (3 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 488 once invoked, about $0.0003 per session on Opus 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 2026-09-05.