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 agents/chadixearth/graphyloop/operating-rulesgit clone --depth 1 https://github.com/chadixearth/graphyloopWhat 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 | $0.00027 | $0.00644 |
| Opus 5 | $0.00014 | $0.00322 |
| Sonnet 5 | $0.00005 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
operating-rules 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Rules — Global
1. Scope & precedence
- User's explicit instruction
- Project AGENTS.md /
.opencode// opencode.json - This file
- Conventions inferred from existing code
Never silently ignore a rule. Override → say which and why in one line.
2. Context discovery
Before modifying code: read nearest AGENTS.md, package manifest + lockfile, linter/formatter config, and 2-3 similar existing files. Mirror their naming, structure, and idioms. Flag deprecated/insecure patterns instead of copying them.
3. Scope discipline
- Smallest correct change. No drive-by refactors, renames, dep bumps, or formatting sweeps.
- Prefer editing existing files over creating new ones.
- Adjacent problems → "Noticed, not changed" list. Do not fix unbidden.
- Large refactors → propose plan first; implement only after approval.
4. Security
- No hardcoded secrets, tokens, or credentials. Committed secret found → stop and flag immediately.
- Parameterized queries only. Encode/escape all user-rendered output. Validate all external input.
- Never weaken or disable auth, TLS, CSRF, or rate limits — not even "temporarily for testing."
- Least privilege on any permission/IAM/config change.
5. Dependencies
Existing project deps → stdlib → new dep (last resort). New dep: one-line justification (what, why existing can't, maintained + no critical CVEs). Respect lockfile.
6. Quality
- Match existing patterns. Formatter is authority on style — don't hand-format. Don't reformat lines you didn't change.
- Names describe intent. Comments explain why, not what. No commented-out code.
- Fail fast with specific error types. Never catch-and-ignore. Validate at trust boundaries.
- Every behavior change ships with tests. Test observable behavior including failure paths.
7. Verification
Run tests, linter, and type-checker before presenting work. If you couldn't run them, say so. Never imply they passed.
8. Guardrails — confirm before:
- Deleting/overwriting files or data not created this session
- DB migrations/seeds on non-local environments
git push --force, history rewrites, tagging, releasing- CI/CD, IaC, or production config changes
- Global installs or system-level changes
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 · 61 lines · 27 tokens per session scan A e6aaf313523b
operating-rules is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 15d ago), licensed MIT. It adds 27 tokens to every session and 644 once invoked, about $0.0001 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 agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
practice-scout
Gather modern best practices and pitfalls for the requested change.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
design-reviewer
Design lead + expert design critic. Two modes: Mode A — authors the project's root DESIGN.md (design identity) at project start. Mode B — reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UI…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…