What is textrawl AGENTS.md?

A project guide for coding agents working on Textrawl, covering first-run setup, safety rules, and available tools. It points to other files for the full commands and architecture.

Use it when setting up Textrawl, running its development or desktop tools, checking agent safety requirements, or keeping the MCP tool inventory in sync.

It gives agents a shared starting point and helps prevent sensitive database or API credentials from being exposed. It also keeps the listed tools consistent with the codebase and documentation.

textrawl AGENTS.md — Instructions file by jeffgreendesign

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/jeffgreendesign/textrawl/agents-md

Clone the repo

git clone --depth 1 https://github.com/jeffgreendesign/textrawl

Made for: Codex, OpenCode.

Per session 510 This file is loaded in full into every session.

When invoked 510 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00510	$0.00510
Opus 5	$0.00255	$0.00255
Sonnet 5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured 2d ago against content hash 874a2a8236a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

textrawl 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 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.

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 · 42 lines

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.

AGENTS.md

Agent/developer operating guide for Textrawl.

For the full reference (commands, architecture, conventions, AX rules), see CLAUDE.md. This file holds only items that are agent-specific or not yet folded into CLAUDE.md.

Onboarding (first run)

pnpm install
pnpm setup
pnpm dev
# optional
pnpm desktop:dev
pnpm inspector

Safety rules

Never log, print, or commit DATABASE_URL or API_BEARER_TOKEN.
Keep server-only secrets server-side. Do not place database credentials in desktop renderer code, website bundles, or client config files.
Treat desktop distribution as client-like: only call server APIs from the desktop app, never embed privileged database credentials.

MCP tool inventory

Kept here so scripts/tool-sync-check.sh can verify the list stays in sync with src/tools/ and README.md. See CLAUDE.md for groupings and README.md for full descriptions.

Workflow (compact normal surface): ask, search, get_document, capture, remember, daily_briefing, timeline
Document/search: search, get_document, list_documents, update_document, add_note
Memory: remember_fact, build_knowledge, query_memory, relate_entities, forget_entity, extract_memories
Conversation: save_conversation_context, query_conversations, delete_conversation
Insights: get_insights, discover_connections, dismiss_insight
Stats: get_stats, health_check
Unified: ask, daily_briefing, save_url, timeline
Postgres: pg_analyze, pg_recommendations, pg_report_history

Repo-specific gotchas

CodeQL mode: this repo uses the advanced workflow in .github/workflows/codeql.yml. Keep GitHub Code Scanning Default Setup disabled in repo settings — enabling it causes SARIF processing conflicts.
pnpm-only: preinstall runs only-allow pnpm; npm/yarn installs will fail.
MCP stdout: any console.log in the MCP request path corrupts JSON-RPC. Use logger from src/utils/logger.js.

Read the full file on GitHub · 42 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.

2d ago First seen · 42 lines · 510 tokens per session scan A 874a2a8236a2

Subscribe to this mod's changes

textrawl AGENTS.md is an instructions file published in the GitHub repository jeffgreendesign/textrawl (5 stars, last pushed 1mo ago), licensed MIT. It adds 510 tokens to every session, about $0.0026 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.

ai-agents document-search keyword-search markdown mcp semantic-search

textrawl AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Onboarding (first run)

Safety rules

MCP tool inventory

Repo-specific gotchas

What this file has done since we first saw it

Other instructions, from other repositories

mcp-memory-service CLAUDE.md

firecrawl CLAUDE.md

siyuan AGENTS.md

mq commit.instructions.md

core copilot-instructions.md

codemark GEMINI.md