solana-developer-platform: Instructions file for Codex

AGENTS.md

solana-developer-platform AGENTS.md is an instructions file for Codex, OpenCode from solana-foundation/solana-developer-platform. It costs 2,747 tokens per session, scanned A, original, MIT.

A repository guide for the Solana Developer Platform, a project with APIs, a web dashboard, documentation, and shared TypeScript packages. It identifies the source files for public APIs, documentation navigation, and generated reference material.

In plain words
What is it for?
Use it when modifying the platform API, dashboard, documentation, shared types, public AI resources, or the scripts that regenerate them.
Why use it?
It helps contributors change the correct source files and avoid editing documentation or API artifacts that are generated automatically.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is solana-foundation/solana-developer-platform's own configuration. It tells Codex and OpenCode 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.md
Clone the repo
git clone --depth 1 https://github.com/solana-foundation/solana-developer-platform

Made for: Codex, OpenCode.

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 solana-developer-platform AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/solana-foundation/solana-developer-platform/agents-md"><img src="https://agentmods.dev/badge/instructions/solana-foundation/solana-developer-platform/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,747 This file is loaded in full into every session.
When invoked 2,747 The same file — it is already loaded in full.
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 $0.02747 $0.02747
Opus 5.5 $0.01099 $0.01099
Sonnet 5.5 $0.00549 $0.00549
Haiku 4.5 $0.00275 $0.00275

Measured yesterday against content hash a2de2e75f495, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solana-developer-platform AGENTS.md 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 yesterday.

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.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solana Developer Platform

This file is the canonical agent guide for this repository.

Repo layout

  • apps/sdp-api: Node.js API deployed to Cloud Run, OpenAPI source, route handlers, Postgres/Redis integrations
  • apps/sdp-web: dashboard application
  • apps/sdp-docs: public documentation site and generated API reference
  • packages/sdp-types: shared runtime types and shared product constants
  • packages/sdp-design-tokens: shared design tokens (CSS custom properties, Tailwind theme mapping) and the refresh theme scope; see its README
  • packages/sdp-ui: the dashboard's UI primitives (@sdp/ui) over @solana/design-system and the design tokens; apps/sdp-web/src/components/ui/* re-exports them; see its README

Source of truth

  • Public API contract: apps/sdp-api/src/openapi/**
  • Public docs navigation: apps/sdp-docs/content/docs/meta.json
  • Generated API docs: apps/sdp-docs/content/docs/reference/api/**
  • AI discovery resources: apps/sdp-docs/public/llms.txt and apps/sdp-docs/public/llms-full.txt

Generated files

Do not hand-edit generated artifacts. Regenerate them with the owning script.

  • OpenAPI JSON: pnpm -C apps/sdp-api openapi:generate
  • Route actions inventory (apps/sdp-api/src/openapi/route-actions.generated.json): pnpm -C apps/sdp-api route-actions:generate
  • API playground catalog: pnpm generate:api-playground
  • API reference docs: pnpm -C apps/sdp-docs generate:api
  • AI discovery resources: pnpm -C apps/sdp-docs generate:ai

Public vs internal surfaces

Public docs and AI artifacts should mirror the supported public surface only.

  • Public API families are the ones the deployment's release channel runs (SDP_RELEASE_CHANNEL; prod runs stable, stage beta, dev experimental), so no deployment documents a route it refuses with 403. Every surface derives from the module stages in packages/sdp-types/src/release-channels.ts and the route inventory in apps/sdp-api/src/routes/route-modules.ts; never hand-maintain another list or move content to hide a module.
    • Public OpenAPI: createPublicOpenApiDocument({ releaseChannel }) in apps/sdp-api/src/openapi/spec.ts drops other modules' routes, and openapi/release-channel-values.ts drops their enum values, examples and oneOf branches from shared schemas (classify a new wallet-binding permission or wallet purpose there; an action's owner comes from the registry in packages/sdp-types/src/actions.ts). The API serves /openapi.json and /llms.txt for its own channel at runtime.
    • Docs site, API reference, Postman and llms*.txt: the docs build reads SDP_RELEASE_CHANNEL (required on Vercel, set per environment like sdp-web; the Dockerfile build arg defaults to experimental). The API writes what the channel publishes (modules and ramp providers, Earn's hold included) to a manifest the docs build reads. Gates follow module declarations: a page about one module takes module: <module> frontmatter (or rampProvider: <provider>), shared pages never name a module, and lists of modules, providers or operations are generated blocks (see apps/sdp-docs/CLAUDE.md, "Release Channels"). Committed generated artifacts are built at experimental (an unset channel), so CI drift checks see every module; CI also checks links on stable.
    • API playground: the committed catalog holds every channel's operations with their module; the dashboard filters it, and the hand-authored forms, by its own channel.
  • earn is held out of every public surface until launch (PRO-2038), independently of its release-channel stage: EARN_PUBLIC_SURFACE_PUBLISHED in apps/sdp-api/src/openapi/spec.ts drops the family from the public OpenAPI document, and the API reference, Postman collection, playground catalog and AI files regenerate from it. Flipping it back is a PRO-1872 security sign-off PR. The internal document and the runtime are unchanged, except GET /v1/projects/{projectId}/provider-availability, which omits Earn entries while the flag is false so the response matches the public document.
  • Hidden/internal families stay out of public AI resources unless product policy changes: admin, onboarding, auth, organizations, members, api-keys
  • Earn has two access tiers. Only strategy catalogue reads, deposit and withdrawal previews, withdrawal-route discovery, and unsigned instant deposit/direct-withdrawal builds may be keyless. Queued request and cancellation builds, submits, tenant reads, programs, custody routes, and the aggregate movement feed always require authentication. Keep this matrix aligned across the router, the internal OpenAPI document and the Embedded Yield guide, which is unpublished until PRO-2038 and lives at apps/sdp-docs/content/unpublished/guides/embedded-yield.mdx, outside the built content/docs tree.
  • Promoting a route into the public OpenAPI document is a security-relevant scope change, not a docs edit: the PR needs a named security sign-off. For earn the pinned list in apps/sdp-api/src/openapi/spec.test.ts enforces this (see apps/sdp-api/src/routes/earn/CLAUDE.md, "Public OpenAPI promotion").

Read the full file on GitHub · 119 lines

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. yesterday Changed · +2 lines · +25 tokens per session a2de2e75f495
  2. 2d ago Changed · +5 lines · +177 tokens per session 13edcae19ae0
  3. 5d ago Changed · +6 lines · +143 tokens per session 41b059adf256
  4. 6d ago Changed · +14 lines · +326 tokens per session 2fac03a1bd65
  5. 8d ago Changed · +9 lines · +512 tokens per session 167d2d6131da
  6. 9d ago Changed · -4 tokens per session 1713ee597fc5
  7. 12d ago Changed · +33 tokens per session 6f0873f249a6
  8. 15d ago Changed · +6 lines · +131 tokens per session d1c84c602928
  9. 16d ago Changed · +1 lines · +50 tokens per session a0de42fe6a86
  10. 18d ago First seen · 76 lines · 1,354 tokens per session scan A 251aa0ba3dc3

Subscribe to this mod's changes

solana-developer-platform AGENTS.md is an instructions file published in the GitHub repository solana-foundation/solana-developer-platform (58 stars, last pushed today), licensed MIT. It adds 2,747 tokens to every session, about $0.0110 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 2026-08-30.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,649 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens