Borrowing it
Nothing to install: this file belongs to Minh-Tam-Solution/tinysdlc. 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/Minh-Tam-Solution/tinysdlc/main/CLAUDE.mdgit clone --depth 1 https://github.com/Minh-Tam-Solution/tinysdlcWrote 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/minh-tam-solution/tinysdlc/claude-md)<a href="https://agentmods.dev/instructions/minh-tam-solution/tinysdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/minh-tam-solution/tinysdlc/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/minh-tam-solution/tinysdlc/claude-md"><img src="https://agentmods.dev/badge/instructions/minh-tam-solution/tinysdlc/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 | $0.04544 | $0.04544 |
| Opus 5 | $0.02272 | $0.02272 |
| Sonnet 5 | $0.00909 | $0.00909 |
| Haiku 4.5 | $0.00454 | $0.00454 |
Grade D, and why
tinysdlc CLAUDE.md scanned grade D with 3 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `src/lib/shell-guard.ts` — 8 mandatory deny patterns for CLI spawn paths (rm -rf, fork bomb, mkfs, dd, device write, shutdown, chmod 777, curl|sh). `guardCommand()`, `isWithinWorkspace()`, `fullGuard()`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `src/lib/shell-guard.ts` — 8 mandatory deny patterns for CLI spawn paths (rm -rf, fork bomb, mkfs, dd, device write, shutdown, chmod 777, curl|sh). `guardCommand()`, `isWithinWorkspace()`, `fullGuard()`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `src/lib/shell-guard.ts` — 8 mandatory deny patterns for CLI spawn paths (rm -rf, fork bomb, mkfs, dd, device write, shutdown, chmod 777, curl|sh). `guardCommand()`, `isWithinWorkspace()`, `fullGuard()`. How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE AI PROJECT CONTEXT — TinySDLC
Version: 0.1.0 Status: Active Last Updated: 2026-02-18
SDLC Compliance
This project follows MTS-SDLC-Lite v1.0.0 — the MIT-licensed community edition of SDLC methodology 6.1.0 — at LITE tier. All SDLC concepts (stages, roles, gates, teams, governance) are documented in MTS-SDLC-Lite. For enterprise tiers (STANDARD/PROFESSIONAL/ENTERPRISE) with enforced governance, audit trails, and policy-as-code, contact MTS.
| Aspect | Value |
|---|---|
| SDLC Methodology | MTS-SDLC-Lite v1.0.0 (based on SDLC 6.1.0) |
| Tier | LITE (1-2 developers) |
| Config | .sdlc-config.json |
| Active Stages | 00-foundation, 01-planning, 02-design, 03-integrate, 04-build |
| Current Gate | G0.1 |
| SDLC Reference | MTS-SDLC-Lite (MIT, all concepts documented) |
Documentation Standards
- All docs follow the
docs/NN-stage/folder structure - Document names use kebab-case (no sprint numbers, dates, or versions in filenames)
- Documents include SDLC headers (SDLC Version, Stage, Status, Authority)
- See
docs/README.mdfor full documentation index
When Creating New Documents
-
Place in the correct stage folder (
docs/00-foundation/throughdocs/04-build/) -
Use feature-based naming:
feature-description.md(kebab-case) -
Add the SDLC header template at the top:
# TinySDLC - [Title] **SDLC Version**: 6.1.0 **Stage**: NN - STAGE_NAME **Status**: Active **Authority**: CTO Approved -
Forbidden in filenames: sprint numbers, dates, versions, team names, person names
Project Overview
TinySDLC is a multi-agent, multi-team, multi-channel 24/7 AI assistant orchestrator that implements MTS-SDLC-Lite for AI+Human team governance. It runs AI agents (Claude Code CLI, OpenAI Codex CLI, or Ollama) organized into teams with 12 SDLC roles: 8 SE4A agents (Researcher, PM, PJM, Architect, Coder, Reviewer, Tester, DevOps), 3 SE4H advisors (CEO, CPO, CTO at STANDARD+), and 1 Router (Assistant). Messages arrive from Discord, WhatsApp, Telegram, Zalo OA, and Zalo Personal through a file-based queue system with atomic operations. Agents collaborate via [@teammate: message] tags, enabling chain execution and parallel fan-out within teams.
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.
- 8d ago First seen · 296 lines · 4,544 tokens per session scan D 2879f75b0cce
tinysdlc CLAUDE.md is an instructions file published in the GitHub repository Minh-Tam-Solution/tinysdlc (10 stars, last pushed 6mo ago), licensed MIT. It adds 4,544 tokens to every session, about $0.0227 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).
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).
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.
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.