tendem-task

tendem-task is a command for Claude Code from Toloka/tendem-mcp. It costs 25 tokens per session (360 once invoked), scanned A, original, MIT.

A pre-compaction hook that runs two Node.js scripts before the agent’s conversation context is shortened. One manages the read cache and the other tracks activity.

In plain words
What is it for?
Running cache preparation and tracking before context compaction. It does nothing when the required scripts are missing.
Why use it?
It records or prepares information before context is compacted, which can help preserve useful state. The available description does not specify what data the tracker stores.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the tendem plugin — 3 commands, 1 agent shipped together

Good fit Running cache preparation and tracking before context compaction. It does nothing when the required scripts are missing.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/toloka/tendem-mcp/tendem-task
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Toloka/tendem-mcp

Made for: Claude Code.

Or install tendem, the plugin that ships this one along with the rest of its 3 commands, 1 agent.

Wrote 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.

agentmods badge for tendem-task

README.md
[![agentmods](https://agentmods.dev/badge/commands/toloka/tendem-mcp/tendem-task/github.svg)](https://agentmods.dev/commands/toloka/tendem-mcp/tendem-task)
Your own site
<a href="https://agentmods.dev/commands/toloka/tendem-mcp/tendem-task"><img src="https://agentmods.dev/badge/commands/toloka/tendem-mcp/tendem-task/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.

agentmods 80×15 button for tendem-task

Your own site · 80×15
<a href="https://agentmods.dev/commands/toloka/tendem-mcp/tendem-task"><img src="https://agentmods.dev/badge/commands/toloka/tendem-mcp/tendem-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00360
Opus 5 $0.00013 $0.00180
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 9d ago against content hash ad07602f95b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tendem-task 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 9d 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.

plugins/tendem/commands/tendem-task.md · 29 lines

What it actually says

Submit a new Tendem task from this instruction: $ARGUMENTS

Follow the tendem-tasks skill. Fidelity first:

  1. Call create_task nowdescription is the user's instruction above, passed as faithfully as possible. Add only context the user actually stated (input files by name, a deadline if one was given). Do NOT expand it into a synthesized brief, and do NOT pre-ask the user clarifying questions — scoping is Tendem's job. Derive a short name (≤120 chars) and reuse a stable conversation_id for this conversation.
  2. If the instruction references local files, upload them immediately after creating the task (get_file_upload_url + the skill's scripts/tendem-upload.sh, then the naming send_message).
  3. Scoping loop: poll with get_task(task_id, wait_for_change_seconds=30), answer Tendem's questions from conversation context via send_message, escalate to the user only when the answer isn't in context or scope/deliverables/deadline are at stake.
  4. Stop when the quote is ready (next_action=await_user_approval): call get_contract(task_id) for the full scope + price, show the user both, and wait for their explicit go-ahead before approve_task.

Report the task_id in your reply so it can be referenced later.

Changes

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.

  1. 9d ago First seen · 29 lines · 25 tokens per session scan A ad07602f95b6

Subscribe to this mod's changes

tendem-task is a command published in the GitHub repository Toloka/tendem-mcp (102 stars, last pushed 19d ago), licensed MIT. It adds 25 tokens to every session and 360 once invoked, about $0.0001 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.