DQIII8: Instructions file for Claude Code

CLAUDE.md

DQIII8 CLAUDE.md is an instructions file for Claude Code from senda-labs/DQIII8. It costs 1,369 tokens per session, scanned C, original, MIT.

Architecture instructions for DQIII8, an automated system that classifies requests, finds relevant knowledge, chooses a model, performs actions, and stores history. It can be used through Telegram or command-line tools.

In plain words
What is it for?
Use them when changing request routing, model tiers, databases, action logging, hooks, skills, agents, or the system's memory and execution flow.
Why use it?
They document the request pipeline, model-selection rules, databases, and required logging paths so changes do not bypass the system's operational rules.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 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 DQIII8 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. 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/senda-labs/DQIII8/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

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 DQIII8 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/senda-labs/dqiii8/claude-md/github.svg)](https://agentmods.dev/instructions/senda-labs/dqiii8/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/senda-labs/dqiii8/claude-md"><img src="https://agentmods.dev/badge/instructions/senda-labs/dqiii8/claude-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 DQIII8 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/senda-labs/dqiii8/claude-md"><img src="https://agentmods.dev/badge/instructions/senda-labs/dqiii8/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,369 This file is loaded in full into every session.
When invoked 1,369 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.01369 $0.01369
Opus 5 $0.00685 $0.00685
Sonnet 5 $0.00274 $0.00274
Haiku 4.5 $0.00137 $0.00137

Measured 10d ago against content hash d9b01c1df933, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

DQIII8 CLAUDE.md scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Destructive / irreversible actions (DROP, live-schema change, `rm -rf` of data) → STOP, notify, wait.
CLAUDE.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DQIII8 — Architecture Kernel

Autonomous AI orchestration engine (VPS, SSH-only). UI: Telegram @YourBotName | CLI: dq cc / dq loop / dq status

Routing Tiers (Cost-First — STRICT)

Anthropic-only vigente (directiva usuario 2026-08-18): Sonnet (default) → Opus (plan-review/ revisión adversarial final únicamente). Cadena multi-tier gratuita (C→B→B+→B++) DORMANTE, no eliminada — ver .claude/rules_db/archive/multi-tier-dormant-2026-08.md. Full table + decision algorithm → .claude/rules/03_tiering_and_routing.md

System Map

  • DQ Pipeline (7 steps): Classify → Retrieve → Gate → Amplify → Route → Execute → Memory
  • DB: database/dqiii8.db (schema_v2.sql — source of truth, now also holds session_memory; sibling: dqiii8_knowledge.db knowledge/vector. dqiii8_history.db and dqiii8_metrics.db.old are frozen post-migration artifacts)
  • Writing to agent_actions: use bin/core/action_log.py's shared helpers (resolve_project_safe(), generate_request_id()) — never hand-build the row. Column families and trigger contract: .claude/rules/01_database_mutations.md
  • Hooks (15): .claude/hooks/ | Skills (22): .claude/skills/ | Agents (17): .claude/agents/
  • Contextual rules (11): .claude/rules_db/ — not read directly; injected per tool call by rules_dispatcher.py — 2 files minimum (_ALWAYS), 13 in the reachable ceiling case, drawn from both .claude/rules_db/ and .claude/rules/ (see .claude/rules/02_hooks_and_permissions.md). Counts on this line are validator-enforced (check_claude_md_counts() in validate_rules_registry.py).
  • Entry: bin/core/openrouter_wrapper.py | Director: bin/director.py
  • Dispatch (CC↔dqiii8): bin/core/dispatch.py — thin subprocess shim; sync + async via detached worker + atomic JSON envelope

New audit reports and audit docs are never committed — full stop. Both docs/audits/*.md and database/audit_reports/*.md are gitignored with no negation, so anything written today stays untracked. Their durability does NOT come from git — it comes from two independent off-VPS channels: bin/tools/backup_audit_docs.sh (mutual Netcup↔Hostinger rsync, dated snapshots, no --delete mirror) and bin/tools/telegram_audit_backup.py (per-file upload to a single allowlisted Telegram chat). Both read their targets/credentials from env vars only. Deleting an untracked file under either path is effectively irreversible once both backups roll — treat these files with the same care as tracked ones even though git status won't show them. Exception, already in history: commit af869db (2026-08-18) deliberately force-added 35 pre-2026-08-18 files under database/audit_reports/ as a one-time archival decision — git ls-tree -r HEAD --name-only database/audit_reports | wc -l confirms 35 tracked today. That corpus is grandfathered, not a precedent: don't git add -f a new audit doc into either directory without the same explicit human call that created this exception.

Read the full file on GitHub · 62 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. 10d ago First seen · 62 lines · 1,369 tokens per session scan C d9b01c1df933

Subscribe to this mod's changes

DQIII8 CLAUDE.md is an instructions file published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 22d ago), licensed MIT. It adds 1,369 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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 · 7,296 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 · 5,153 tokens

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

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

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 · 4,469 tokens