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/indexnetwork/index/pr-reviewergit clone --depth 1 https://github.com/indexnetwork/indexWhat 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 | $0.00592 | $0.00592 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00118 | $0.00118 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
index pr-reviewer.instructions.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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Layering
- Flag any controller that imports directly from an adapter (e.g.
drizzle.ts,database.adapter.ts) — controllers must delegate to services only. - Flag any service that imports another service — use events, queues, or shared lib for cross-service orchestration.
- Flag any agent file that imports from the database schema or adapters — agents must remain pure and receive dependencies via constructor injection.
- Flag any
@indexnetwork/protocolpackage code that imports from the app layer (services/api/src/) — the protocol package must be fully self-contained.
TypeScript
- Flag any use of
anytype — useunknownand narrow, or a concrete type. - Flag agent input/output types not validated with Zod schemas.
- Flag manual type definitions where Drizzle inference (
$inferSelect,$inferInsert) would suffice. - Flag imports from
lib/schema— always import fromsrc/schemas/database.schema.ts.
Optional / Nullable Columns in Drizzle Upserts
- When an upsert writes an optional column as
col: value ?? nullorcol: value ?? undefined, check whether this clobbers an existing non-null value on the conflict update path. The preferred pattern is a conditional spread:...(value !== undefined ? { col: value } : {})— this omits the column entirely when omitted by the caller, so the DB default or existing row value is preserved. - This applies equally to
.values()and.set()in.onConflictDoUpdate().
Database & Migrations
- Flag any migration file that does not follow the naming pattern
{NNNN}_{action}_{target}[_{detail}].sql(e.g.0001_add_chat_session_share_token.sql). - Flag hard deletes (
DELETE FROMor Drizzle.delete()) in service code where soft deletes (deletedAt) should be used instead. - Flag schema changes in
database.schema.tsthat lack a corresponding new migration file.
Version Bumping
- Flag changes to
packages/cli/orpackages/protocol/that lack a version bump in their respectivepackage.json.
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 · 42 lines · 592 tokens per session scan A 7812fb893764
index pr-reviewer.instructions.md is an instructions file published in the GitHub repository indexnetwork/index (132 stars, last pushed 4d ago), licensed MIT. It adds 592 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
agent-skills AGENTS.md
Instructions for ClickHouse/agent-skills, covering agents.md, repository overview, repository structure, creating a new skill and directory structure.
contexture sql.instructions.md
Instructions for AcKeskin/contexture, covering sql rules, sql formatting, sql query structure and sql schema and ddl.
atlas-mcp-server CLAUDE.md
Instructions for cyanheads/atlas-mcp-server, covering claude.md, essential development commands, build and development, database operations and running the server.
cognitive-core CLAUDE.md
Claude Code instructions for mocartlex-wq/cognitive-core, covering claude.md — cognitive core, build & run, сборка и запуск всех сервисов, пересборка только api and просмотр логов.
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.