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/zjy1346/openthesis/agents-mdgit clone --depth 1 https://github.com/zjy1346/OpenThesisWrote 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/zjy1346/openthesis/agents-md)<a href="https://agentmods.dev/instructions/zjy1346/openthesis/agents-md"><img src="https://agentmods.dev/badge/instructions/zjy1346/openthesis/agents-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 | $0.01186 | $0.01186 |
| Opus 5 | $0.00593 | $0.00593 |
| Sonnet 5 | $0.00237 | $0.00237 |
| Haiku 4.5 | $0.00119 | $0.00119 |
Grade A, and why
OpenThesis 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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenThesis Agent Workflow
Roles
- The primary agent keeps the model selected for the current main task. Do not override or rewrite the primary model configuration.
- All spawned subagents for this repository must use the project-configured
lunahighagent. Multiplelunahighsubagents may be used when parallel work is genuinely useful or necessary. - The primary agent owns requirement interpretation, complex diagnosis, architecture, implementation planning, tradeoff and security decisions, final diff review, and acceptance.
lunahighowns bounded execution after the primary agent has made the necessary decisions.
User approval and release workflow
Every user-requested software modification must follow this workflow:
- On the first conversational round for a new modification request, do not modify application code or implement the requested feature. Creating or updating the change-record Markdown file described below is allowed.
- During that first round, locate the source of the problem or the relevant implementation area, explain the cause or current behavior when it can be determined, and report a proposed solution to the user. The agent may ask focused questions or present implementation choices when needed.
- In that same first round, create a Markdown change record named after the planned target version, such as
1.4.1.md. The file must record every requested change, the proposed solution or decisions still requiring user choice, relevant scope or files when known, and a checklist that can later be used for acceptance. - Do not modify application code, add features, or begin implementation until the user explicitly approves the proposed modification.
- After the user approves implementation, perform the authorized code and feature changes. Delegation to
lunahighmust still follow the role, ownership, and concurrency rules in this document. - After implementation, perform acceptance against the corresponding
<version>.mdchange record. Verify every recorded user requirement individually. Do not claim the work is complete while any recorded requirement is missing, only partially implemented, or unverified. - Once all recorded requirements pass acceptance, build and package a release artifact for the user to test.
- Wait for the user to test the release artifact. Only after the user explicitly states that everything is working correctly and explicitly authorizes uploading or publishing to GitHub may the project create the final Git commit, push changes, and publish the new GitHub Release.
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 · 67 lines · 1,186 tokens per session scan A 813e7dabb74a
OpenThesis AGENTS.md is an instructions file published in the GitHub repository zjy1346/OpenThesis (51 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,186 tokens to every session, about $0.0059 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
wanaku CLAUDE.md
Claude Code instructions for wanaku-ai/wanaku, covering wanaku, core guidelines, quick start, build info and architecture.
ase AGENTS.md
AGENTS.md instructions for rse/ase, covering about, repository layout, build system, setup and cli commands.
ai-native-sdlc AGENTS.md
Instructions for bashebr/ai-native-sdlc, covering agents.md, source of truth, validation and conventions.
dbt-llm-agent CLAUDE.md
Instructions for pragunbhutani/dbt-llm-agent, covering project description, monorepo structure, monorepo projects, monorepo project rules and other services used.
prompt-pro markdown-content-instructions.instructions.md
Documentation and content creation standards.
prompt-pro copilot-instructions.md
Instructions for timothywarner-org/prompt-pro, covering prompt-pro ai guidance, purpose and scope, repository layout, the only runnable code and authoring rules.