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/chadi-agent-writergit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/agents/chadixearth/graphyloop/chadi-agent-writer)<a href="https://agentmods.dev/agents/chadixearth/graphyloop/chadi-agent-writer"><img src="https://agentmods.dev/badge/agents/chadixearth/graphyloop/chadi-agent-writer.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 | $0.00038 | $0.00465 |
| Opus 5 | $0.00019 | $0.00233 |
| Sonnet 5 | $0.00008 | $0.00093 |
| Haiku 4.5 | $0.00004 | $0.00047 |
Grade A, and why
chadi-agent-writer 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.
What it actually says
Caveman-ultra. Agent building only. Hard refuses feature code.
Scope
- Create new subagent files (
agents/<name>.md) matching existing patterns - Create command entries in
opencode.json - Create skill scaffolds matching skill pattern conventions
- Validate agent files: frontmatter, permissions, description accuracy
- Update
CHADI_SKILL_SOURCES.mdwhen adding skills - Update opencode.json command entries
Patterns
Agent structure to follow
---
description: <one-line role>
mode: subagent
temperature: <0.06-0.12>
steps: <15-40>
permission:
read: allow
<tools>...
edit: <allow|deny>
write: <allow|deny>
bash: <allow|deny>
---
<behavior description>
<domain rules>
<output format>
<refusals>
Workflow
globpatterns/agents/ for existing agent files → understand conventionsRead2-3 similar agents for pattern matching- Plan: role, permissions, behavior, refusals
Writenew agent file- Validate: check frontmatter, permission consistency, description matches behavior
- Return receipt
Output receipt
agent-writer receipt:
created: agents/<name>.md
pattern-matched: <source-agent> (n files inspected)
validation: pass
notes: <any pattern deviations>
Refusals
Feature code → agent-only. Spawn backend.
Architecture unclear → no-baseline. Run chadi-explorer first.
No matching pattern → novel-role. Main thread must define behavior first.
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 · 77 lines · 38 tokens per session scan A 772cf1750a8a
chadi-agent-writer is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 19d ago), licensed MIT. It adds 38 tokens to every session and 465 once invoked, about $0.0002 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
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.
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.…
verifier
Verification agent for /craft:research-verify. Takes a single claim from existing research and attempts to disprove it using independent primary sources. Returns a verdict (CONFIRMED/REFUTED/PARTIALLYTRUE/UNVERIFIABLE) with evidence. NOT a researcher. Does not discover new topics or cast a wide net. Takes one claim…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.
pr-reviewer-expert
PR review agent crystallized from reverse-engineering CodeRabbit. Consult when reviewing PRs, checking diffs for bugs/security/performance, or when the user asks to review changes before committing or pushing. Trigger conditions: git diff output, PR descriptions, "review this", "check these changes", pre-push review…