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 agentmods add instructions/centrifuge/api-v3/agents-mdgit clone --depth 1 https://github.com/centrifuge/api-v3Wrote 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/instructions/centrifuge/api-v3/agents-md)<a href="https://agentmods.dev/instructions/centrifuge/api-v3/agents-md"><img src="https://agentmods.dev/badge/instructions/centrifuge/api-v3/agents-md.svg" alt="Measured on agentmods" 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 | $0.04663 | $0.04663 |
| Opus 5 | $0.02331 | $0.02331 |
| Sonnet 5 | $0.00933 | $0.00933 |
| Haiku 4.5 | $0.00466 | $0.00466 |
Grade A, and why
api-v3 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 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.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cfg-api-v3 — AI & contributor guide
Centrifuge protocol indexer: Ponder ingests EVM logs/blocks → src/handlers/ → src/services/ → PostgreSQL (Drizzle); GraphQL while running. Setup/ops: README.md. Extra Cursor rules: .cursor/rules/*.mdc (always-on summary: cfg-api-v3-core.mdc).
Hard rules
- Handlers — Only under
src/handlers/. Subscribe withmultiMapper(...)orponder.on(...). Thin: decodeevent.args, orchestrate; no heavy domain logic here. - No DB in handlers — No
context.db.*, Drizzle builders, or raw SQL. Use services. Exception: callsnapshotterfor snapshot inserts (do not duplicate that pattern). - No ad-hoc Ponder handler DB — Persistence lives in entity services on
Service.ts; do not inlinecontext.dbin handlers. - Batching — Prefer
insertMany/saveMany; query once, update in memory, batch-save when it fits. generated/— Never edit. Regenerate viapnpm update-registry,pnpm codegen, or build/start tooling; fix registry/upstream instead.
Services
- Shape: one service per main schema entity (or tight group).
export class EntityService extends Service<typeof Table> { static readonly entityTable = Table; static readonly entityName = "EntityName"; }— seeAdapterService.ts. Statics (onService):insert,insertMany,saveMany,get,getOrInit,upsert,query,count; instancesave/delete. Add methods for shared business rules. - Logging —
serviceLog/serviceErrorfromlogger.ts;expandInlineObjectfor record-shaped logs. Every meaningful public/static method (DB, side effects, non-trivial branches) logs at least once; trivial pure accessors (e.g. shallowread()) need not.serviceLogis a no-op underponder start;serviceErrorstill logs — seelogger.ts. - Handlers never call
context.db.sql/context.db.find; they callFooService.get(...)etc. Base layer uses Drizzle internally. - Batch upserts — Extending
saveMany: followService.tscomment; usesql.raw(\excluded."column"`)for Ponder’s PG proxy, not brokenexcluded` expansions.
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.
- 3d ago First seen · 228 lines · 4,663 tokens per session scan A 9bb0a517cc35
api-v3 AGENTS.md is an instructions file published in the GitHub repository centrifuge/api-v3 (5 stars, last pushed 6d ago), licensed MIT. It adds 4,663 tokens to every session, about $0.0233 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 2026-08-31.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.