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 theYahia/WWmcp --skill complete-taskgit clone --depth 1 https://github.com/theYahia/WWmcpWrote 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/theyahia/wwmcp/complete-task)<a href="https://agentmods.dev/skills/theyahia/wwmcp/complete-task"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/complete-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/theyahia/wwmcp/complete-task"><img src="https://agentmods.dev/badge/skills/theyahia/wwmcp/complete-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00024 | $0.00577 |
| Opus 5.5 | $0.00010 | $0.00231 |
| Sonnet 5.5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
complete-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 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.
What it actually says
/complete-task — Завершить BPM-задачу
Алгоритм
- Найди задачу:
get_tasks(kind — все / входящие / исходящие / с моим участием, closed, filter) или сразуget_task(id), если ID известен. - Из карточки задачи запомни два идентификатора: id самой задачи и instanceId экземпляра процесса —
complete_taskтребует оба. get_task_exits(id) — доступные исходы задачи. Это обязательный шаг: exitId нельзя угадать, у каждой задачи свой набор.- Покажи пользователю список исходов и дождись выбора. Завершение задачи двигает бизнес-процесс дальше и необратимо.
complete_task(id, exitId, instanceId, context) — заверши. В context кладутся значения полей формы, если исход их требует.- Задача не наша или нужен другой исполнитель —
reassign_task(id, userId) вместо завершения. ID сотрудника ищи черезget_users(фильтр) илиget_user_by_id. - Если по задаче нужно оставить след —
add_commentдля элемента приложения, к которому она относится (namespace, code, id элемента); история —get_comments.
Важно
complete_taskбез предварительногоget_task_exitsвызывать нельзя: неверный exitId либо отклоняется, либо уводит процесс не по той ветке.- instanceId — это ID экземпляра процесса, а не ID задачи. Перепутанные значения дают отказ.
- Если исход требует заполненной формы, а context пуст, ELMA365 вернёт ошибку валидации — сначала спроси у пользователя значения полей.
Формат ответа
## Задача abc-123 — Согласование договора
**Статус**: В работе · **Экземпляр процесса**: inst-77f0
**Исполнитель**: Иванов И.
### Доступные исходы
1. Согласовать (exitId: approve)
2. Отправить на доработку (exitId: rework)
Завершено по исходу «Согласовать». Процесс перешёл на следующий шаг.
Примеры
/complete-task abc-123
/complete-task abc-123 согласовать
/complete-task переназначь abc-123 на Петрова
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 · 47 lines · 24 tokens per session scan A 6626a5883b17
complete-task is a skill published in the GitHub repository theYahia/WWmcp (36 stars, last pushed 27d ago), licensed MIT. It adds 24 tokens to every session and 577 once invoked, about $0.0001 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 2026-09-06.
Other skills, from other repositories
gitlab-work-items
Find, inspect, create or update GitLab issues and other work items, including explicitly requested planning follow-ups. Use for GitLab work items, not GitHub issues, and do not infer permission to publish from a request to brainstorm.
gitlab-discovery
Find a GitLab project or namespace and establish the exact target for follow-up repository, merge request, work-item or CI work. Use for GitLab project discovery, not local filesystem search or GitHub repositories.
create-handoff
Create a bounded handoff for another agent or person on the board with handoffsend, after confirming the recipient, the request and the sensitivity with the user.
pm
Project Manager skill. One orchestrator session drives eight subagent roles -- planner, plan-reviewer, doer, reviewer, deployer, integ-test-runner, ci-watcher, harvester -- through cycles of Plan, Develop, Test, and Harvest across one or more parallel tracks in isolated git worktrees, running each task on a…
accept-handoff
Accept a queued or blocked handoff addressed to the user with handoffacknowledge, after reading it in full with handoffget.
close-handoff
Close or park a handoff with handoffupdatestatus, marking it completed or blocked as its recipient, or cancelled as its sender while it is still queued.