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/thienhm/loci/agents-mdgit clone --depth 1 https://github.com/thienhm/lociWhat 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 | $0.00627 | $0.00627 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
loci 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 yesterday.
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.
This is a copy
89% identical to OpenAIWorkshop copilot-instructions.md — 122 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow Orchestration
1. Plan Node Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately - don't keep pushing
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity
2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One task per subagent for focused execution
3. Self-Improvement Loop
- After ANY correction from the user: update
tasks/lessons.mdwith the pattern - Write rules for yourself that prevent the same mistake
- Ruthlessly iterate on these lessons until mistake rate drops
- Review lessons at session start for relevant project
4. Verification Before Done
- Never mark a task complete without proving it works
- Diff behavior between main and your changes when relevant
- Ask yourself: "Would a staff engineer approve this?"
- Run tests, check logs, demonstrate correctness
5. Demand Elegance (Balanced)
- For non-trivial changes: pause and ask "is there a more elegant way?"
- If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
- Skip this for simple, obvious fixes - don't over-engineer
- Challenge your own work before presenting it
6. Autonomous Bug Fixing
- When given a bug report: just fix it. Don't ask for hand-holding
- Point at logs, errors, failing tests - then resolve them
- Zero context switching required from the user
- Go fix failing CI tests without being told how
Task Management
- Plan First: Write plan to
tasks/todo.mdwith checkable items - Verify Plan: Check in before starting implementation
- Track Progress: Mark items complete as you go
- Explain Changes: High-level summary at each step
- Document Results: Add review section to
tasks/todo.md - Capture Lessons: Update
tasks/lessons.mdafter corrections
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.
- yesterday First seen · 72 lines · 627 tokens per session scan A b3d3e0ecf0b7
loci AGENTS.md is an instructions file published in the GitHub repository thienhm/loci (0 stars, last pushed 3mo ago), licensed MIT. It adds 627 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to OpenAIWorkshop copilot-instructions.md, differing in 122 lines, and is treated as a copy.
Other instructions, from other repositories
claude-code-mastery CLAUDE.md
Instructions for ShipWithAI/claude-code-mastery, covering claude.md — claude code mastery course, project overview, course structure, directory layout and teaching methodology: progressive hands-on hybrid.
student-llm-wiki AGENTS.md
Instructions for IssacW228/student-llm-wiki, covering student llm wiki — agent instructions, 操作规则 operation rules, token预算规则（最高优先级）, 架构 architecture and 命令 commands.
calc-mcp CLAUDE.md
Instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.
claude-for-designers CLAUDE.md
Instructions for mshadmanrahman/claude-for-designers, covering claude for designers: how to work in this folder, what this folder is, when the student asks about the folder, orient them, work out which class they are on before you answer and answer keys: never open one unasked.
get-fable AGENTS.md
Instructions for imMamdouhaboammar/get-fable, covering get-fable repository instructions, purpose, working contract, canonical lifecycle packs and runtime semantics.
umbel CLAUDE.md
Instructions for jahala/umbel, covering umbel — project guidelines for claude code, what this is, non-negotiable principles, architecture layers (strict downward dependency) and stack.