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/paulduvall/ai-development-patterns/agents-mdgit clone --depth 1 https://github.com/PaulDuvall/ai-development-patternsWhat 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 | $0.00747 | $0.00747 |
| Opus 5 | $0.00374 | $0.00374 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
ai-development-patterns 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Task Tracking
Tasks live in .tasks/backlog.jsonl — an append-only JSONL file, one task per line, git-tracked. There is no daemon and no database: the file is the record and git is the history.
Do NOT use TodoWrite, TaskCreate, markdown TODO lists, or bd/beads — this repo migrated off beads on 2026-08-17.
A task's state is its LAST line. The file is append-only, so grep '"status": *"open"' also matches tasks that were later closed, over-reporting the open set. Always fold last-line-wins:
python3 -c "import json;last={};[last.__setitem__(t['id'],t) for t in map(json.loads,filter(str.strip,open('.tasks/backlog.jsonl')))];print('\n'.join(f\"{i} {t['title'][:68]}\" for i,t in last.items() if t['status']=='open'))"
Close a task by APPENDING a new line with status set to closed; never edit or delete an existing line. Work discovered while doing another task gets its own line with discovered_from set to the parent id.
Schema: {id, title, status, blocks[], depends_on[], spec_ref, created, priority, description, discovered_from?} — status is open or closed; priority is 1 (most urgent) to 4; a task is ready when every id in depends_on is closed. Issue ids keep their original beads form so existing commit messages still resolve.
The full beads history is archived verbatim at .tasks/beads-archive.jsonl.
Pattern Adoption Evaluation
Run model-backed pattern-adoption research only through the repository-local
$evaluate-pattern-adoption skill in an interactive, signed-in local Codex client.
Never run it in GitHub Actions, expose evaluator API keys to the repository, or bypass either the
exact plan approval or the separate draft-PR publication approval. Use no more than three
read-only research subagents at once, keep the root task as the sole writer, and use a fresh
read-only verifier for every batch. GitHub Actions is limited to deterministic validation and
read-only link/content checks for this capability.
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 · 55 lines · 747 tokens per session scan A e6b418a447b9
ai-development-patterns AGENTS.md is an instructions file published in the GitHub repository PaulDuvall/ai-development-patterns (645 stars, last pushed 3d ago), licensed MIT. It adds 747 tokens to every session, about $0.0037 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 2026-08-30.
Other instructions, from other repositories
awesome-claude AGENTS.md
AGENTS.md instructions for JSONbored/awesome-claude, covering heyclaude agent instructions, project intent, source of truth, contribution and content policy and safety and privacy metadata.
claude-code CLAUDE.md
Instructions for PaulDuvall/claude-code, covering claude.md, project overview, core philosophy, key principles and repository structure.
awesome-claude CLAUDE.md
Claude Code instructions for JSONbored/awesome-claude, a project described as: HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.
video-clip-agent CLAUDE.md
Instructions for neopen/video-clip-agent, covering penclip — 视频混剪智能体, 当前状态, 分层架构（依赖方向：外层 → 内层，内层禁止反向依赖）, bridge 层（向后兼容转发，勿在此改逻辑） and 关键入口.
FrameCode-VibeWork AGENTS.md
Instructions for Sistema2D/FrameCode-VibeWork, covering agents.md, instruction order, reading-trigger rule, regression rule and when a plan is required.
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.