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/tooppoo/enozunu/agents-mdgit clone --depth 1 https://github.com/tooppoo/enozunuWrote 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/tooppoo/enozunu/agents-md)<a href="https://agentmods.dev/instructions/tooppoo/enozunu/agents-md"><img src="https://agentmods.dev/badge/instructions/tooppoo/enozunu/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 | $0.00340 | $0.00340 |
| Opus 5 | $0.00170 | $0.00170 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
enozunu 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- enozunu CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Instructions
Worktree
- When making file changes, always use the
git-kuraskill unless the user explicitly instructs otherwise. - Follow the workflow defined by the
git-kuraskill. Do not duplicate or reinterpret that workflow in this file.
Pull Request
- Use
.github/pull_request_template.mdas template.
Review-sized implementation
In implementation, priority is given to minimizing the amount of information a human reviews at one time over completing the entire issue.
Implement only a single, minimum unit of review that can be judged independently, and stop as soon as it becomes ready for review. Do not proceed to subsequent units before approval is granted.
Divide multiple major decisions, behavioral changes, mechanical refactorings, and peripheral cleanups if they can be reviewed independently.
Skill usage
- When updating documentation, always use the
documentation-writingskill. - When writing or modifying code comments, always use the
documentation-writingskill. - When After completing file edits, before reporting completion, unless the user explicitly instructs otherwise, always use the
subagent-review-loopskill. - When writing or modifying code comments, always use the
code-commentskill. - When design or implemnts CLI output, always use the
cli-output-designskill. - When implments e2e test, always use the
reportageskill. - When during implementation work, always use the
review-sized-implementationskill. - When access to github remote to push, pull, create PR, create Issue and other, always use the
github-cliskill.
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.
- 6d ago First seen · 32 lines · 340 tokens per session scan A 98e89662f777
enozunu AGENTS.md is an instructions file published in the GitHub repository tooppoo/enozunu (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 340 tokens to every session, about $0.0017 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
kodama AGENTS.md
Instructions for amergrgic/kodama, covering agents, architecture, agent roster, conventions and validation.
agent-powerups CLAUDE.md
Instructions for yeaight7/agent-powerups, covering claude.md, commands, architecture, catalog.json — single source of truth and cli command routing (src/cli/apx.ts).
agent-powerups GEMINI.md
Instructions for yeaight7/agent-powerups, covering project overview, main technologies, architecture/structure, building and running and development conventions.
agent-powerups AGENTS.md
Instructions for yeaight7/agent-powerups, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
open-agents AGENTS.md
AGENTS.md instructions for vercel-labs/open-agents, covering agents.md, quick links, authentication, database & migrations and environment isolation.
relay AGENTS.md
AGENTS.md instructions for AgentWorkforce/relay, covering git workflow rules, never push directly to main, correct workflow, ... do work .. and stop here - let user merge.