docdex AGENTS.md

Repository instructions for Docdex, a local service that stores searchable project and user memory and provides information about code relationships. They require agents to use memory and dependency-graph tools when making changes.

In plain words
What is it for?
Use them when working in the Docdex repository, especially for changes involving stored memory, symbols, dependencies, or project impact.
Why use it?
They help an agent recall relevant context, save new facts and preferences, and understand which code may be affected before editing.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/bekirdag/docdex/agents-md
Clone the repo
git clone --depth 1 https://github.com/bekirdag/docdex

Made for: Codex, OpenCode.

Per session 9,725 This file is loaded in full into every session.
When invoked 9,725 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.09725 $0.09725
Opus 5 $0.04862 $0.04862
Sonnet 5 $0.01945 $0.01945
Haiku 4.5 $0.00972 $0.00972

Measured 2d ago against content hash cda3f31166ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docdex AGENTS.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Use impact analysis for every code change: prefer MCP tools `docdex_impact_graph` / `docdex_dag_export` (IPC/HTTP). If shell networking is blocked, do not use curl; use MCP/IPC instead. If unavailable, state it and pro
AGENTS.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

---- START OF DOCDEX INFO V0.2.99 ---- Docdex URL: http://127.0.0.1:28491 Use this base URL for Docdex HTTP endpoints. Health check endpoint: GET /healthz (not /v1/health).

Priority Directives (Mandatory)

  • Always use both memory lobes early: docdex_get_profile + docdex_memory_recall; save new facts via docdex_memory_save and new preferences via docdex_save_preference.
  • Profile memory is always-on and global; never gate on DOCDEX_ENABLE_MEMORY or repo state. docdex_save_preference must persist (fallback if embeddings/LLM unavailable). If profile calls fail, treat it as a bug.
  • Maintain agent-specific profile memory: use your agent_id with docdex_get_profile/docdex_save_preference; store generic self-knowledge (role, tooling, preferences).
  • Use impact analysis for every code change: prefer MCP tools docdex_impact_graph / docdex_dag_export (IPC/HTTP). If shell networking is blocked, do not use curl; use MCP/IPC instead. If unavailable, state it and proceed cautiously.
  • Apply DAG reasoning for planning: prefer dependency graph facts (impact results and /v1/dag/export) to choose the right change order and scope.
  • Use Docdex tools intentionally: docdex_search/symbols/ast for repo truth; docdex_stats/files/repo_inspect/index for index health.
  • When session history matters, use conversation-memory tools intentionally: archive/search/read with docdex_conversation_*, build compact context with docdex_wakeup, record durable notes with docdex_diary_*, and inspect temporal graph state with docdex_kg_* instead of replaying full transcripts.
  • For folder structure, use docdex_tree instead of raw rg --files/find to avoid noisy folders.
  • When you do not know something, run docdex_web_research (force_web=true). Web research is encouraged by default for non-repo facts and external APIs.
  • When a Docdex feature makes a task easier/safer, you MUST use it instead of ad-hoc inspection. Examples: docdex_search for context, docdex_open//v1/snippet for file slices, docdex_symbols/docdex_ast for structure, docdex_impact_graph/docdex_impact_diagnostics for dependency safety, and docdex_dag_export to review session traces.
  • For dependency/library docs, run docdexd libs discover/docdexd libs fetch and search with include_libs rather than web searching.
  • For test execution, use docdexd run-tests (or docdexd test run-node) instead of ad-hoc commands when feasible.
  • For daemon stability triage, prioritize FD hardening checks: startup nofile warning threshold (DOCDEX_MIN_NOFILE_SOFT), profile lock retry knobs (DOCDEX_PROFILE_LOCK_MAX_ATTEMPTS, DOCDEX_PROFILE_LOCK_RETRY_BASE_MS), installer pressure defaults (DOCDEX_REPO_IDLE_SECONDS, DOCDEX_REPO_HIBERNATE_SECONDS, DOCDEX_REPO_CLEANUP_INTERVAL_SECONDS), and docs/ops/fd_exhaustion_playbook.md.
  • For staged-change validation, use docdexd hook pre-commit.
  • For MCP client registration, use docdexd mcp add (or --all) instead of editing configs by hand.

Read the full file on GitHub · 560 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. 2d ago First seen · 560 lines · 9,725 tokens per session scan A cda3f31166ad

Subscribe to this mod's changes

docdex AGENTS.md is an instructions file published in the GitHub repository bekirdag/docdex (16 stars, last pushed 6d ago), licensed MIT. It adds 9,725 tokens to every session, about $0.0486 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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 · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 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 · 4,345 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens