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.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/CLAUDE.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote 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/senda-labs/dqiii8/claude-md)<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.
<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>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 5.1 | $0.01324 | $0.01324 |
| Opus 5.5 | $0.00530 | $0.00530 |
| Sonnet 5.5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00132 | $0.00132 |
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 1mo 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.
- Acción destructiva/irreversible (DROP, cambio de schema en vivo, `rm -rf` de datos) → STOP, How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DQIII8 — Working Charter
Autonomous AI orchestration engine (VPS, SSH-only). Enfoque, metodología y exigencias viven
aquí. Estado del sistema (DBs, excepciones puntuales, backups) vive en docs/ARCHITECTURE.md.
Comportamiento base siempre cargado: .claude/rules/00_core_behavior.md — este fichero no lo
repite, solo añade lo que ese no cubre.
Enfoque — Enterprise-Grade Bar
- Verifica el artefacto final real (servicio desplegado, respuesta de API, DOCX entregable, fila de DB) — tests y logs no cuentan como verificación.
- Si algo no se pudo verificar (p.ej. UI sin navegador disponible), dilo explícitamente. Nunca reportes éxito sin haberlo comprobado.
- El listón es corrección verificada, no volumen: no autoriza a exceder el alcance pedido
(Priority Ladder,
00_core_behavior.md). - Un error que se repite exige una comprobación estructural que bloquee la entrega hasta resolverse — no un parche puntual.
Metodología — lo que no cubre 00_core_behavior.md
- Una ronda de aclaración afilada vale más que varios ciclos de corrección: si el prompt no fija objetivo + alcance + listón de "hecho", pregunta antes de iterar.
- Feature nueva no trivial →
/speckitantes de entrar en modo plan (.claude/rules_db/dqiii8-speckit.md). - Cost-first: el tier más barato capaz. Estado vigente de qué proveedor está operativo hoy no se
fija aquí (cambia) —
00_core_behavior.md§ REGLA NIM es la SSOT siempre cargada.
Protocolos de ejecución
- Plan ≤5 pasos, sin acciones destructivas → ejecuta autónomo, notifica después.
- Plan toca ≥3 módulos O alcance ambiguo → modo plan primero, espera confirmación, luego
/panel-review <plan-file>(veredicto asesor, no gate — consume la única escalada a Opus por tarea; SSOT.claude/skills/panel-review/). - Escritura en corpus de gobernanza (
.claude/{hooks,rules,rules_db,agents,skills}/) → ESCALATE, espera confirmación humana antes de proceder. - Un DENY del PermissionAnalyzer es final: no reintentes, no reordenes, no
--no-verify/--force. Reconduce o pide al humano — nunca lo bordees. - Acción destructiva/irreversible (DROP, cambio de schema en vivo,
rm -rfde datos) → STOP, avisa, espera. Excepciones ya cerradas en código (SSOT.claude/rules/02_hooks_and_permissions.md):rm -rfde build/cache auto-aprobado;git push --forcedenegado sin excepción. - Bug en producción → arréglalo ya: lee logs, aísla la causa, resuelve, verifica. Sin escoltas.
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.
- 1mo ago Changed · +11 lines · -45 tokens per session 748da40acff3
- 1mo ago First seen · 62 lines · 1,369 tokens per session scan C d9b01c1df933
DQIII8 CLAUDE.md is an instructions file published in the GitHub repository senda-labs/DQIII8 (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,324 tokens to every session, about $0.0053 per session on Opus 5.5. 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.