Borrowing it
Nothing to install: this file belongs to pedrocivita/tocket. 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/pedrocivita/tocket/main/AGENTS.mdgit clone --depth 1 https://github.com/pedrocivita/tocketWrote 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/pedrocivita/tocket/agents-md)<a href="https://agentmods.dev/instructions/pedrocivita/tocket/agents-md"><img src="https://agentmods.dev/badge/instructions/pedrocivita/tocket/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/pedrocivita/tocket/agents-md"><img src="https://agentmods.dev/badge/instructions/pedrocivita/tocket/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 | $0.00846 | $0.00846 |
| Opus 5.5 | $0.00338 | $0.00338 |
| Sonnet 5.5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
tocket 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Tocket
Single source any AI agent should read first. Cursor, Claude, Gemini, Copilot, Windsurf, Codex, and anyone else that can read files.
Tocket is the project notebook. Agents work. Tocket remembers. Jev only chooses the next step.
What Tocket is
- A file convention (
.context/) plus a small CLI. - Not a chatbot, not a computer-use runtime, not codegen.
- Jev (or the stub) is the judge, not the writer. Workers (you) execute.
Read before expensive tools
- This file.
.context/activeContext.mdand.context/systemPatterns.md.- The latest file under
.context/decisions/if one exists.
Phrase: Before expensive tools: tocket decide --dry-run, or read .context/decisions/.
Decide vs work
| Command | Who | What |
|---|---|---|
tocket decide |
Jev or stub | Writes the next move as JSON. Does not run tools. |
tocket work |
Reference worker | Dry-run plan (default). Never calls Jev. |
tocket work --apply |
Reference worker | Notebook receipt only. Honors tool_gate. |
If a decision file already exists, honor it. Do not call tocket decide again. Do not re-ask Jev.
Tool-risk gate
Before bash, deploy, or browser:
tocket decide --from state.json --choice tool_gate:allow,block,ask --shadow
tocket work --from <decision>
tocket work --from <decision> --apply
allowor notool_gatefield: apply as usual.block: stop (exit 2).ask: escalate to a human (exit 2).--forceoverrides the gate.- Shadow / log-only apply still needs
--force.
Meta-attention and packs
Harness your context. Jev is the judge, not the writer. Meta-attention handoff: Jev judges chunks; workers read the filtered handoff. tocket handoff --aware scores .context/ chunks (batched Noul relevant and Score relevance) and writes .context/handoffs/ plus a receipt under .context/attention/. --dry-run or no TYPESAFE_API_KEY uses the stub; a key plus --shadow is live and log-only. Conditional packs live in .context/gotchas/ (frontend.md, path-src-api.md, or ## sections). tocket packs load --query asks Noul "load this pack?" and writes .context/active/packs.md. Without --aware, tocket handoff stays the full session summary. The flow is still decide, then work, then tool_gate. Agent auto-config is unchanged.
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.
- 1mo ago Changed · +4 lines · +208 tokens per session 12e7df73724d
- 1mo ago First seen · 70 lines · 638 tokens per session scan A 844fe8efdfbe
tocket AGENTS.md is an instructions file published in the GitHub repository pedrocivita/tocket (38 stars, last pushed 1mo ago), licensed MIT. It adds 846 tokens to every session, about $0.0034 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 2026-09-21.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.