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/Toloka/tendem-mcpWrote 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/toloka/tendem-mcp/tendem-lifecycle)<a href="https://agentmods.dev/rules/toloka/tendem-mcp/tendem-lifecycle"><img src="https://agentmods.dev/badge/rules/toloka/tendem-mcp/tendem-lifecycle.svg" alt="Measured on agentmods" 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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
tendem-lifecycle 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 7d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tendem MCP lifecycle
This workspace uses Tendem to delegate work to vetted human experts. You (the agent) submit a task on the user's behalf; Tendem scopes it in a chat, returns a price quote, and once the user approves, a human expert executes it and returns results as markdown plus downloadable files.
The tools are named mcp__tendem__* (or mcp__plugin_tendem_tendem__* when
plugin-bundled). If absent, the connector isn't connected — tell the user to
connect the tendem MCP server in their client's MCP settings and complete the
OAuth login. For the full walkthrough, the tendem-tasks skill and the
server's tendem-quickstart prompt are the source of truth.
The path
create_task (+ uploads) → SCOPING LOOP → quote → user approves → approve_task
poll ⇄ answer │
▼
EXECUTION LOOP → next_action=fetch_result → get_task_result
create_task— pass the user's own formulation faithfully; do not expand it into a synthesized brief or pre-interrogate the user. Tendem drives scoping.- Scoping loop:
get_task(task_id, wait_for_change_seconds=30), answer Tendem's questions from conversation context viasend_message. - Approval gate: when the quote is ready, call
get_contract(task_id)for the full scope + price (get_taskomits these details), surface price + scope, and get the user's explicit go-ahead beforeapprove_task. This is a spend. - Execution loop: poll a few times, then hand off — nothing is lost between sessions.
get_task_result— present the markdown, savefiles[]under./tendem/<task_id>/.
Rules of the road
- Offer, don't hijack. If the skill surfaced only because a task could use a human, offer Tendem as an option and create a task only after the user says yes.
- Spend needs explicit approval. Never call
approve_taskwithout showing the price and scope and getting a clear yes. - Never busy-loop. Trust the envelope's
next_action/poll_after_seconds/guidance. Usewait_for_change_seconds=30long-polls, poll silently, and hand off after a handful of unchanged rounds. - A scope-change request voids the quote. Never show a stale price; keep polling until a fresh quote arrives.
- Insufficient balance is not a retry.
approve_taskreturns a task-boundtopup_url— give it to the user; never loop onapprove_task. - Data scraping is refused by policy — automated data-extraction tasks won't be accepted, and rephrasing doesn't change that. Don't submit them.
- One unit of work per task. If the work pivots, create a new task (same
conversation_id).
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.
- 7d ago First seen · 60 lines · 727 tokens per session scan A 8a0e4eebd060
tendem-lifecycle is a cursor rule published in the GitHub repository Toloka/tendem-mcp (102 stars, last pushed 17d ago), licensed MIT. It adds 727 tokens to every session, about $0.0036 per session on Opus 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
slice-tasks
PLANNING SPINE STEP 2 of 3 — Slice the work: break a scoped PRD into vertical-slice stories in specs/epics/. Use after scope-work (step 1), before plan-work (step 3). Not a substitute for scope-work or plan-work.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
feedback-enhanced
Rules for an interactive feedback system that lets users and an AI agent discuss complex development work in real time. It includes guidance for recording decisions, tracking progress and handling detailed inputs such as code and diagrams.
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
linear-in-review
After finishing a Linear issue, set its status to In Review (never Done).
sprint-planning
BMAD BMM Agent: sprint-planning.