Borrowing it
Nothing to install: this file belongs to zackbart/connecta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zackbart/connecta/main/AGENTS.mdgit clone --depth 1 https://github.com/zackbart/connectaWrote 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/zackbart/connecta/agents-md)<a href="https://agentmods.dev/instructions/zackbart/connecta/agents-md"><img src="https://agentmods.dev/badge/instructions/zackbart/connecta/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/zackbart/connecta/agents-md"><img src="https://agentmods.dev/badge/instructions/zackbart/connecta/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03815 | $0.03815 |
| Opus 5.5 | $0.01526 | $0.01526 |
| Sonnet 5.5 | $0.00763 | $0.00763 |
| Haiku 4.5 | $0.00381 | $0.00381 |
Grade A, and why
connecta 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 2d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on connecta
This is the canonical agent instruction file. CLAUDE.md is its symlink;
keep it that way. Connecta aggregates remote MCP servers and HTTP APIs behind one
MCP endpoint. Agents use JavaScript through execute_code, with direct calls
for known operations and writes. One fetch-native core runs on Node and
Cloudflare Workers, with Effect inside and Promises at the published edge.
Read PRINCIPLES.md before changing a subsystem, then use the
agent documentation index to select the task guide
and contract sections. Architecture maps the
implementation; subsystem source and tests establish current behavior.
README.md owns the short human-facing product overview and setup
handoff. guides/ owns human-facing explanations of the mental model,
agent connections, and safety. Keep exact behavior, configuration references,
contracts, and runnable deployment setup in agent docs. This file owns
repository policy; scoped skills and provider guides own their task-specific
detail. Update the owning contract when changing behavior, and keep the README
and explanatory guides consistent without adding a configuration reference.
The completed rework plan of record #703
records owner decisions that supersede older guidance wherever they conflict.
decisions/ explains past choices without binding later PRs.
spec/coverage.json records current MCP support, gaps,
and test evidence. Describe planned work as planned, not shipped behavior.
The roadmap lives in GitHub issues:
file new work with motivation, behavior, and acceptance criteria, not a TODO.md.
Shipped documentation audience
Write documentation/, templates/, and examples/worker/
first for an agent operating a deployment from the installed package. Route
operator tasks through node_modules/@zackbart/connecta/documentation/README.md.
Write README.md and guides/ for people: short, explanatory, and visual.
Guides may illustrate a concept with a small example, but own no contracts or
complete setup procedures; link to documentation/ for those and keep the
explanations consistent with it. guides/ ships in the npm package so README
links also work for installed-package readers. The same neutral-name rule below
applies to the README and guides.
State every operator convention as self-contained rules with a neutral example;
decision records and issues may explain why, never supply required steps.
decisions/, spec/, and .claude/ do not ship. Separate contributor-only
source maps, INV citations, and implementation/test evidence under clearly
labeled contributor headings; operator tasks must not need them. Use neutral
names (assistant, alice, bob, crm, tickets, notes_alice,
[email protected]), never real deployments, clients, people, or organizations.
Maintained provider product names remain valid.
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.
- 2d ago Changed · +15 lines · +284 tokens per session 73348b7a1675
- 8d ago Changed · +3 lines · +66 tokens per session 4dd26cc9af15
- 9d ago Changed · -18 lines · -376 tokens per session b224d6d0dac3
- 10d ago Changed · +3 lines · +54 tokens per session 703021744e55
- 13d ago Changed · +29 lines · +492 tokens per session 89727677b919
- 15d ago Changed · +17 lines · +87 tokens per session 230036802685
- 16d ago Changed · +44 lines · +722 tokens per session c228b28fe22f
- 20d ago Changed · +29 lines · +407 tokens per session 9eb74fe795dc
- 23d ago Changed · +7 lines · +141 tokens per session a2c9be5fa54c
- 28d ago First seen · 129 lines · 1,938 tokens per session scan A cae7309f28b7
connecta AGENTS.md is an instructions file published in the GitHub repository zackbart/connecta (0 stars, last pushed yesterday), licensed MIT. It adds 3,815 tokens to every session, about $0.0153 per session on Opus 5.5. 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.
connecta AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| connecta AGENTS.mdzackbart/connecta | Instructions file | 0 | yesterday | MIT | A | 3,815 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |