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/leshchenko1979/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/leshchenko1979/fast-mcp-telegram/implementation-workflow)<a href="https://agentmods.dev/rules/leshchenko1979/fast-mcp-telegram/implementation-workflow"><img src="https://agentmods.dev/badge/rules/leshchenko1979/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/leshchenko1979/fast-mcp-telegram/implementation-workflow"><img src="https://agentmods.dev/badge/rules/leshchenko1979/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.
Copies of this mod
1 near-identical copy found in the catalogue:
- implementation-workflow — 100% identical, 0 lines differ
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 leshchenko1979/fast-mcp-telegram (49 stars, last pushed 10d 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. 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
example
You are in a workspace with Bifrost MCP tools enabled. Use them for code navigation, understanding, and modification. Follow these guidelines.
mcp
Rules written in Chinese for choosing an enhancement service based on the user's request. They cover feature changes, bug analysis, and project or architecture analysis.
bootstrap-alwayson
Minimal always-required LLM fixes.
monitoring
Monitoring, observability, and alerting rules.
data-fetching
Data fetching patterns with TanStack Query, Server Components, and Supabase.
token-efficiency
Token optimization rules to reduce AI costs by 30%+.