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.
git clone --depth 1 https://github.com/HoangP8/toklessWrote 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/rules/hoangp8/tokless/context-tools)<a href="https://agentmods.dev/rules/hoangp8/tokless/context-tools"><img src="https://agentmods.dev/badge/rules/hoangp8/tokless/context-tools/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/rules/hoangp8/tokless/context-tools"><img src="https://agentmods.dev/badge/rules/hoangp8/tokless/context-tools.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 | $0.00631 | $0.00631 |
| Opus 5.5 | $0.00252 | $0.00252 |
| Sonnet 5.5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
context-tools 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 12d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Tools (context-mode)
MCP tools ctx_* keep large or uncertain analysis out of context.
Rules
| Tool | Role | Replaces |
|---|---|---|
ctx_execute |
Run code in sandbox. Only stdout enters context. | Bash for analysis tasks |
ctx_execute_file |
Process file in sandbox. Raw bytes never leave. | Read on large files (>200 lines) |
ctx_batch_execute |
Run N commands + auto-index output. Search in same call. Concurrency 1-8. | Multiple Bash + grep |
ctx_index |
Chunk markdown/text into FTS5. Queryable via ctx_search. |
Manual grep over pasted content |
ctx_search |
Multi-strategy search across indexed content + session memory. Typo correction. | Re-asking user, re-deriving |
ctx_fetch_and_index |
Fetch URL, chunk and index. Cache 24h; ttl: 0 or force: true bypasses cache. Supports requests + concurrency: 1-8. |
Webfetch |
Examples
ctx_execute(language:"shell", code:"git log --oneline -20 | wc -l")
ctx_execute(language:"javascript", code:`
const fs = require('node:fs');
const files = fs.readdirSync('src').filter(f => f.endsWith('.ts'));
const counts = files.map(f => ({
file: f,
lines: fs.readFileSync('src/' + f, 'utf8').split('\n').length
}));
console.log(JSON.stringify(counts));
`)
ctx_execute_file(path:"app.log", language:"javascript", code:`
const lines = FILE_CONTENT.split('\n');
const errs = lines.filter(l => /ERROR|FATAL/.test(l));
console.log(errs.length + ' errors');
`)
ctx_batch_execute(commands:[
{label:"diff", command:"git diff HEAD~1"},
{label:"status", command:"git status"},
], queries:["failures","errors"], timeout:120000, concurrency:2,
cwd:".", query_scope:"batch")
ctx_fetch_and_index(requests:[
{url:"https://docs.example.com/api", source:"api-docs"},
{url:"https://docs.example.com/guide", source:"guide"},
], concurrency:4)
ctx_search(queries:["auth endpoint","rate limits"], source:"api-docs")
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.
- 12d ago Changed · +7 lines · +49 tokens per session ca8a8233bbc5
- 1mo ago First seen · 58 lines · 582 tokens per session scan A 713e1e8e5417
context-tools is a cursor rule published in the GitHub repository HoangP8/tokless (290 stars, last pushed today), licensed MIT. It adds 631 tokens to every session, about $0.0025 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 2026-08-30.
Other cursor rules, from other repositories
cursor-memory
Shokunin memory system: persistent context across sessions.
notes
The .cursor/notes folder contains notes about this project. The notes form a knowledge base about the project to be used by the AI Agents working on the project. They should help you when working with the same code again in the future.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.