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.
npx agentmods add instructions/dongduong2001/pudo-code-system/claude-mdgit clone --depth 1 https://github.com/DongDuong2001/pudo-code-systemWrote 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/dongduong2001/pudo-code-system/claude-md)<a href="https://agentmods.dev/instructions/dongduong2001/pudo-code-system/claude-md"><img src="https://agentmods.dev/badge/instructions/dongduong2001/pudo-code-system/claude-md.svg" alt="Measured on agentmods" 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 | $0.00486 | $0.00486 |
| Opus 5 | $0.00243 | $0.00243 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
pudo-code-system CLAUDE.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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Instructions
Use PUDO as the operating workflow for this repository: Plan -> Understand -> Develop -> Optimize.
This root file is the Claude Code memory bridge. It keeps the README integration link valid and points Claude to the fuller Claude-specific guide in claude/CLAUDE.md.
Required Workflow
- Plan before implementation for non-trivial work.
- Inspect relevant files before editing.
- Keep patches small and scoped.
- Preserve existing user changes.
- Run relevant checks, or state why checks were skipped.
- Use quality gates before handoff or release.
Model-Specific Notes
Claude Fable 5
When running on Fable 5 (model: claude-fable-5), leverage the 1M token context for:
- Large refactors spanning 10+ files — include all relevant files in a single context pack
- Long-running autonomous tasks — use session handoff for checkpoints across multi-hour work
- Self-correction loops — Fable 5 can refine its own work without user intervention
Repository References
- Core agent workflow:
AGENTS.md - Claude-specific guide:
claude/CLAUDE.md - Quality gates:
quality/quality-gates.md - QC checklists:
quality/qc-checklists.md - AI output review:
quality/ai-output-review.md - Edge cases:
quality/edge-cases/general.md
Avoid
- Guessing APIs, paths, or file contents.
- Rewriting unrelated files.
- Adding dependencies without justification.
- Removing or weakening tests without approval.
- Hiding failed or skipped verification.
Release & Package Quality
- Maintain npm Package: Evolve the repository while keeping it fully functional as an npm package for the MCP Server.
- Git Branch Workflow: Never work directly on default branch; use dedicated feature branches (e.g.
feature/...). - Commit Strategy: Stage only one file at a time and commit it with a Conventional Commit.
- Semantic Versioning & Changelog: Bump versions using VERSIONING.md and update
CHANGELOG.mdusing CHANGELOG_TEMPLATE.md. Follow RELEASE_CHECKLIST.md and PUBLISH_NPM.md.
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.
- 5d ago First seen · 49 lines · 486 tokens per session scan A 5c4ca9fba5d0
pudo-code-system CLAUDE.md is an instructions file published in the GitHub repository DongDuong2001/pudo-code-system (5 stars, last pushed 29d ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
supergraph AGENTS.md
AGENTS.md instructions for datit309/supergraph, covering supergraph — mandatory workflows, skills, auto language detection, tiered workflow — pick the right tier first and full pipeline (tier 3).
openehr-assistant-plugin AGENTS.md
Instructions for Cadasto/openehr-assistant-plugin, covering ai guidelines: openehr assistant plugin, project overview, domain context, companion mcp server and calling conventions the server enforces.
diffler AGENTS.md
Instructions for jamestkelly/diffler, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
cinematic-ui CLAUDE.md
Instructions for akseolabs-seo/cinematic-ui, covering claude.md, purpose, read first, installation and cross-agent files.
cinematic-ui GEMINI.md
Instructions for akseolabs-seo/cinematic-ui, covering gemini.md, project summary, core workflow, primary platform note and repo guidance.
cinematic-ui copilot-instructions.md
Instructions for akseolabs-seo/cinematic-ui, covering repository custom instructions for github copilot, project goal, important context, if you edit workflow rules and writing style.