solana-developer-platform: Skill for Claude Code

.agents/skills/sdp-review/SKILL.md

sdp-review is a skill for Claude Code, Codex from solana-foundation/solana-developer-platform. It costs 89 tokens per session (2,874 once invoked), scanned A, original, MIT.

A short digest and focused review of changes in the Solana Distribution Platform codebase. A codebase is the collection of source files that make up a software product.

In plain words
What is it for?
Use it to summarize a working diff or branch, identify affected domains and packages, and perform a targeted engineering and product-obligation review.
Why use it?
It explains user-visible changes and implementation details while checking reuse, data parsing, dependencies, transactions, and specified product obligations.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

This is solana-foundation/solana-developer-platform's own configuration. It tells Claude Code and Codex how to work on solana-developer-platform 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 solana-developer-platform configures →

Reuse

Borrowing it

Nothing to install: this file belongs to solana-foundation/solana-developer-platform. 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/solana-foundation/solana-developer-platform/main/.agents/skills/sdp-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/solana-foundation/solana-developer-platform

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 sdp-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/solana-foundation/solana-developer-platform/sdp-review/github.svg)](https://agentmods.dev/skills/solana-foundation/solana-developer-platform/sdp-review)
Your own site
<a href="https://agentmods.dev/skills/solana-foundation/solana-developer-platform/sdp-review"><img src="https://agentmods.dev/badge/skills/solana-foundation/solana-developer-platform/sdp-review/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 sdp-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/solana-foundation/solana-developer-platform/sdp-review"><img src="https://agentmods.dev/badge/skills/solana-foundation/solana-developer-platform/sdp-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,874 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00089 $0.02874
Opus 5 $0.00044 $0.01437
Sonnet 5 $0.00018 $0.00575
Haiku 4.5 $0.00009 $0.00287

Measured 5d ago against content hash 0e031e5cf30e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sdp-review 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 5d 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.

.agents/skills/sdp-review/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Digest a change set into short, scannable bullets, then run a focused review pass (reuse, parsing, dependencies, transactions). Not a full correctness review — the code-review and owasp skills cover that.

1. Base style

Read ../sdp-concise/SKILL.md and apply its output contract. This file reference is the shared Claude/Codex source of truth; do not depend on an agent-specific output-style plugin.

2. Pin the change set

Default scope is the current working diff (git diff + git diff --staged + untracked files). If the user names a base (--base <ref>, a branch, a PR number via gh pr diff), diff against that instead. If the working tree is clean and no base was given, diff the current branch against main.

Read enough of the changed files (and their immediate callers) to describe the change accurately — never summarize from filenames alone.

3. Output

Four sections, bullets only, each bullet one line where possible. Plain language first, code refs second.

Product changes — what a user of the dashboard or API can now do / no longer do / sees differently. If a change is purely internal, say "no user-visible change" and one line why the work exists.

How it's implemented — the technical mechanism per product bullet: new/changed routes, DB migrations + tables, services, providers, UI components. Reference as file:line. Call out money-path mechanics (idempotency, transactions, policy gating) explicitly when present.

Domains touched — which SDP domains this crosses: issuance, ramps (per provider), payments/batches, custody wallets, counterparties/compliance, policy, auth/keys, webhooks, dashboard, docs. One bullet per domain with a half-line of what changed there.

Packages used — two lists:

  • Workspace packages touched or consumed (apps/sdp-api, apps/sdp-web, packages/sdp-types, @sdp/payments, @sdp/policy, …) and what for.
  • External dependencies newly added or leaned on in this change (from package.json diffs and new imports). No new deps → say so in one bullet.

Read the full file on GitHub · 84 lines

Files

What ships with it

1 file 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. 5d ago Changed · +1 lines 0e031e5cf30e
  2. 9d ago First seen · 83 lines · 89 tokens per session scan A 42bdf9c992fb

Subscribe to this mod's changes

sdp-review is a skill published in the GitHub repository solana-foundation/solana-developer-platform (52 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,874 once invoked, about $0.0004 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 2026-08-30.