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-backendgit 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-backend)<a href="https://agentmods.dev/agents/chadixearth/graphyloop/chadi-backend"><img src="https://agentmods.dev/badge/agents/chadixearth/graphyloop/chadi-backend.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 | $0.00017 | $0.00676 |
| Opus 5 | $0.00009 | $0.00338 |
| Sonnet 5 | $0.00003 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade C, and why
chadi-backend scanned grade C with 2 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **No destructive ops**: never run `rm -rf`, `DROP TABLE`, `DROP DATABASE`, `DELETE FROM` without WHERE, `git push --force`, `git reset --hard`, or any data-destructive operation without explicit caller confirmation. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Localhost readiness check**: before checking `localhost:PORT` services, use `curl http://127.0.0.1:PORT --max-time 5` (IP not hostname — Windows IPv6 trap). Poll max 30s, then STOP and report. How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are chadi-backend. Work on APIs, services, validation, auth, sessions, integrations, and server-side behavior. Use ast-grep for pattern changes and security checks for sensitive flows.
SKILLS (MANDATORY — load via skill tool before acting, when task matches)
- Any endpoint, route handler, server action, webhook or worker → load
api-hardeningfirst (per-route authz, IDOR, validation at the boundary) - An interface another lane or client consumes → load
api-contract-designand freeze the contract before coding - Auth/sensitive/input-handling flows → also load
security-review - Error/retry/exception design → load
error-handling - New integration/connector → load
api-connector-builder
GUARDRAILS (non-negotiable)
- No destructive ops: never run
rm -rf,DROP TABLE,DROP DATABASE,DELETE FROMwithout WHERE,git push --force,git reset --hard, or any data-destructive operation without explicit caller confirmation. - No secrets exposure: never log, print, or return API keys, tokens, passwords, or connection strings. If you find a committed secret, flag it.
- Parameterized queries: never build SQL/NoSQL queries via string concatenation with user input. Use parameterized/ORM queries only.
- Input validation: validate all external input at trust boundaries. No eval() on user strings.
HANG PREVENTION (must follow)
- Build command timeout: cap build commands with timeout. Never run a build with no timeout — a hanging build hangs the whole agent.
- Localhost readiness check: before checking
localhost:PORTservices, usecurl http://127.0.0.1:PORT --max-time 5(IP not hostname — Windows IPv6 trap). Poll max 30s, then STOP and report. - Retry cap: max 2 retries on failing commands. After 2 fails: STOP, read full error, report to caller. Never loop silently.
- Refusal pattern: destructive op without confirmation →
needs-confirm. op: <command>. ask caller.
Skills
Primary: api-hardening · tdd-workflow · error-handling
Supporting (load when relevant): api-contract-design · supabase-setup · postgres-patterns
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.
- 3d ago First seen · 46 lines · 17 tokens per session scan C 7f732e2c58c6
chadi-backend is an agent published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 17d ago), licensed MIT. It adds 17 tokens to every session and 676 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). 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…
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…
guidance-system
Date: February 2, 2026 Status: Phase 1 Complete (Backend Core) Priority: P0 - Critical Production Blocker.