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/nestharus/agent-implementation-skill/agents-mdgit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWhat 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 | $0.03952 | $0.03952 |
| Opus 5 | $0.01976 | $0.01976 |
| Sonnet 5 | $0.00790 | $0.00790 |
| Haiku 4.5 | $0.00395 | $0.00395 |
Grade A, and why
agent-implementation-skill 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent-Implementation-Skill
Project Structure
├── governance/ # Project governance layer
│ ├── problems/index.md # Why this code exists (PRB-XXXX)
│ ├── patterns/index.md # How we solve recurring problems (PAT-XXXX)
│ ├── audit/prompt.md # Audit process for external models
│ ├── audit/history.md # Cumulative audit log (105 rounds)
│ ├── design/ # Design rationale documents
│ └── risk-register.md # Landed-code risks and debt
├── philosophy/ # Values and principles
│ ├── design-philosophy-analysis.md
│ ├── design-philosophy-notes.md
│ ├── profiles/PHI-global.md
│ └── region-profile-map.md
├── system-synthesis.md # Architecture + governance connections
├── src/ # Deployed skill code
│ ├── <system>/agents/ # Agent definitions owned by each system (57 agents across 15 systems)
│ ├── scripts/ # Runtime orchestration scripts
│ ├── SKILL.md # Skill entry point
│ ├── implement.md # Implementation pipeline
│ └── ... # Other skill docs
├── evals/ # Evaluation scenarios
└── tests/ # Test suite
Running Sub-Agents
Sub-agents are invoked via the agents binary (~/.local/bin/agents), not through Claude Code's built-in Agent tool. The binary is the CLI mode of Oulipoly Agent Runner.
CLI Syntax
agents [OPTIONS] [AGENT] [PROMPT...]
| Option | Description |
|---|---|
-m, --model <MODEL> |
Execute a model directly (no agent file) |
-a, --agent-file <AGENT_FILE> |
Path to an agent .md file (any location) |
-f, --file <FILE> |
Read prompt from file |
-p, --project <PROJECT> |
Working directory for the subprocess |
--models-dir <MODELS_DIR> |
Override models directory |
--agents-dir <AGENTS_DIR> |
Override agents directory |
Prompt resolution priority: --file > positional arguments > stdin
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 · 381 lines · 3,952 tokens per session scan A 9eec83521fb2
agent-implementation-skill AGENTS.md is an instructions file published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 3,952 tokens to every session, about $0.0198 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
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
notebooklm-skill AGENTS.md
Instructions for claude-world/notebooklm-skill, covering notebooklm-skill, authentication, cli commands, notebooklm-skill — core operations and notebooklm-pipeline — workflow orchestration.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
stockbit-mcp CLAUDE.md
Instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
devin-handoff AGENTS.md
Instructions for club-cog/devin-handoff, covering devin handoff — agent guide, what this is, when to hand off, finding the script and how to use.
agent-plugins-skills copilot-instructions.md
Instructions for richfrem/agent-plugins-skills, covering copilot instructions for agent-plugins-skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.