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.
npx skills add Toloka/tendem-mcp --skill tendem-taskgit 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/skills/toloka/tendem-mcp/tendem-task)<a href="https://agentmods.dev/skills/toloka/tendem-mcp/tendem-task"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/toloka/tendem-mcp/tendem-task"><img src="https://agentmods.dev/badge/skills/toloka/tendem-mcp/tendem-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00044 | $0.00457 |
| Opus 5.5 | $0.00018 | $0.00183 |
| Sonnet 5.5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
tendem-task scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
build fully-substituted `curl` upload commands per the `tendem-tasks` What it actually says
Submit a new Tendem task from the user's instruction — the text accompanying this invocation.
Follow the tendem-tasks skill. Fidelity first:
- Call
create_tasknow —descriptionis the user's instruction, 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 shortname(≤120 chars) and reuse a stableconversation_idfor this conversation. - If the instruction references local files: ⚠️ do not upload them
yourself — OpenAI's security policies block the sandbox from PUTting
files to external storage (an OpenAI platform restriction, not a Tendem
one). Immediately after creating the task, call
get_file_upload_url, build fully-substitutedcurlupload commands per thetendem-tasksskill'sreferences/files.md, and hand them to the user to run on their host machine — telling them the manual step is due to OpenAI's sandbox policy. After the user confirms, send the namingsend_message. - Scoping loop: poll with
get_task(task_id, wait_for_change_seconds=30), answer Tendem's questions from conversation context viasend_message, escalate to the user only when the answer isn't in context or scope/deliverables/deadline are at stake. - Stop when the quote is ready (
next_action=await_user_approval): callget_contract(task_id)for the full scope + price, show the user both, and wait for their explicit go-ahead beforeapprove_task.
Report the task_id in your reply so it can be referenced later.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 34 lines · 44 tokens per session scan A b088896538d6
tendem-task is a skill published in the GitHub repository Toloka/tendem-mcp (102 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 457 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
spec-driven-dev-v2
Use when an agent will work for hours or days across many files and multiple vertical slices. Drives a three-level Project → Sprint → Task hierarchy with isolated per-task execution, a review round-loop, context packs for subagent reviewers, governance-as-code, and orchestrator-readable state. Designed for…
parallel-execution-engine
Use when latency matters and several independent tasks can run at once -- a bounded implementation or investigation that needs waves of concurrent workers, not a persistent completion loop or stage-based orchestration.
subagent-team-orchestration
Use when a task is too large or too mixed for one agent -- it splits into research, planning, implementation, review, and verification stages, needs different specialties, or has parallelizable branches that still share dependencies.
handoff-discipline
Use when ending a session, handing a task back to the user, or approaching the context limit with work unfinished -- the next session or engineer must be able to resume the work instantly.
task-intake
Use at the start of a new task -- before writing or editing code -- when the request is vague, the scope boundaries are unclear, or the acceptance criteria for "done" have not been stated.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.