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/alexeyleshchenko/fast-mcp-telegramWrote 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/alexeyleshchenko/fast-mcp-telegram/implementation-workflow)<a href="https://agentmods.dev/rules/alexeyleshchenko/fast-mcp-telegram/implementation-workflow"><img src="https://agentmods.dev/badge/rules/alexeyleshchenko/fast-mcp-telegram/implementation-workflow/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/alexeyleshchenko/fast-mcp-telegram/implementation-workflow"><img src="https://agentmods.dev/badge/rules/alexeyleshchenko/fast-mcp-telegram/implementation-workflow.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 | $0.01721 | $0.01721 |
| Opus 5.5 | $0.00688 | $0.00688 |
| Sonnet 5.5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
implementation-workflow 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.
This is a copy
100% identical to implementation-workflow — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation workflow
Any code change follows steps 1–5. The user approves at step 3 only (the plan), not implementation diffs.
Start: Plan mode before step 1. No code until explicit step 3 approval.
Steps
| Step | Mode | Action | Gate |
|---|---|---|---|
| 1 | Plan | Scope, files, exit commands, clean-break checks; link checklist rows; learning fields (below). Plan file: ~/.cursor/plans/<task>_*.md only (not in-repo). If scope is too big → scope split. |
Hypothesis, success signal, and kill criteria recorded |
| 2 | Plan | Pre-impl review (code-reviewer, readonly): trim scope; favor simplicity; DX if user-facing; Deferred for cuts; or phase split (below). Revise plan; no code. |
Scope trimmed or split agreed; plan favors simplicity; exits set; Deferred if anything cut; plan stand-alone; incremental edits keep previous plan |
| 3 | Plan → Agent | Present plan; wait for approval; roadmap ask if Deferred (below). | Roadmap ask if Deferred; explicit approval |
| 4 | Agent | Run exit tests/commands; fix failures. No extra confirmation prompts. | Exits green |
| 5 | Agent | Closeout (below): one pass — review, fixes, docs. | Closeout checklist done |
Before step 4: reread CONTRIBUTING.md (Design Philosophy, Code Quality, Development Workflow). Boundaries: design philosophy and tool-count guidelines in CONTRIBUTING; session/MCP patterns in systemPatterns.md.
Step 1 — Learning fields
Record in the plan (short bullets; full sentences optional):
| Field | Purpose |
|---|---|
| Hypothesis | What we believe this change will prove or enable |
| Success signal | What “worked” looks like beyond exit commands (user outcome, metric, or spike claim) |
| Kill / stop | When to abandon or narrow scope before more implementation (failed exit class, wrong approach, scope creep) |
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 First seen · 112 lines · 1,721 tokens per session scan A fe6adde32793
implementation-workflow is a cursor rule published in the GitHub repository alexeyleshchenko/fast-mcp-telegram (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,721 tokens to every session, about $0.0069 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to implementation-workflow, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
swift-development
Swift development: SwiftUI, Combine, async/await, iOS patterns, and Apple platform conventions.
lighter-safety
Safety contract for the Lighter MCP server. Apply whenever a lighter tool is invoked.
nix-security
Nix Security and Sandboxing.
terminal-commands
Guidelines for generating terminal commands that ensure outputs are readable by Cursor agents.
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.