Borrowing it
Nothing to install: this file belongs to rakovi4/continue-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rakovi4/continue-framework/main/.claude/skills/finish-task/SKILL.mdgit clone --depth 1 https://github.com/rakovi4/continue-frameworkWrote 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/rakovi4/continue-framework/finish-task)<a href="https://agentmods.dev/skills/rakovi4/continue-framework/finish-task"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/finish-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/rakovi4/continue-framework/finish-task"><img src="https://agentmods.dev/badge/skills/rakovi4/continue-framework/finish-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 | $0.00034 | $0.00488 |
| Opus 5.5 | $0.00014 | $0.00195 |
| Sonnet 5.5 | $0.00007 | $0.00098 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
finish-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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/finish-task - Complete a Task
Carry any tracked task from its current progress.md cursor through its final
archive without requiring repeated task-execution commands.
Workflow
- Resolve
task Nwith/continue's task lookup rules. If already archived, report its location; archive an active task with no open checkbox. Read its type and the workflow that owns that type. - Read
.claude/templates/workflow/finish-task-coordination.mdcompletely and run its initial scheduling pass. - Read
references/platform-monitoring.md, then start its single five-minute readiness monitor using the exact route for the active platform. Explicitly tell the user when the monitor starts, wakes the coordinator, or causes a newly ready lane to dispatch. - Execute the next work with the template's task-type route. Keep every applicable atomic unit, approval, test, work-log, and commit boundary; replace only the owning workflow's successful intermediate stop with another scheduling pass.
- Delegate only lanes admitted by the template's dependency, ownership, context, and net-speedup gates. The parent remains coordinator and personally validates every result.
- Continue until the task is archived, a required user decision pauses the active workflow, or a sub-skill fails. Stop the monitor before the final report or any pause.
Constraints
- Do not turn the task into multiple competing
/continuesessions. - Do not parallelize merely because agent capacity exists. Simple, short, dependent, or overlapping work stays in the parent.
- Do not overlook frontend/backend concurrency after their shared contract is frozen.
- QA cases are serial; do not fan them out.
- Give workers full available history and the complete task-specific context packet; never delegate from a thin summary.
- Preserve every owning workflow's authorization boundaries and explicit user decisions. This skill changes execution duration, not scope or permission.
- Report intermediate lane and work-unit outcomes while continuing, but emit the owning workflows' full report fields once, aggregated at the terminal stop.
What ships with it
2 files 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 Changed e1f43e149fb0
- 2mo ago First seen · 49 lines · 34 tokens per session scan A 9c861de4f6d9
finish-task is a skill published in the GitHub repository rakovi4/continue-framework (54 stars, last pushed 29d ago), licensed MIT. It adds 34 tokens to every session and 488 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 2026-08-30.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.