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 agentmods add skills/hkuds/openspace/deliverable-completionnpx skills add HKUDS/OpenSpace --skill deliverable-completiongit clone --depth 1 https://github.com/HKUDS/OpenSpaceWhat 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 | $0.00025 | $0.00654 |
| Opus 5 | $0.00013 | $0.00327 |
| Sonnet 5 | $0.00005 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
deliverable-completion 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 3d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deliverable Completion Protocol
Purpose
This skill addresses a common misconception during document and file creation tasks: agents sometimes search for or attempt to use a submit_work, finalize, or similar tool after creating the deliverable. No such step is required. Task completion is achieved when the file is successfully created with the required content.
Core Principle
File creation = Task completion
When a task requests you to create a document, report, script, or any file-based deliverable, the task is complete once:
- The file has been written to disk
- The file contains the required content
- The file is in the correct format and location
There is no additional submission, finalization, or confirmation step needed.
Execution Workflow
Step 1: Create the Deliverable
Use the appropriate file creation method for your task:
# For programmatic file creation
with open('deliverable.docx', 'wb') as f:
f.write(document_content)
# For shell-based creation
echo "content" > output.txt
Or use available tools like write_file, create_file, etc.
Step 2: Verify Creation
Confirm the file exists and contains expected content:
ls -la deliverable.docx
# or
cat output.txt
Step 3: Declare Completion
Once verification passes, the task is complete. Do not:
- Search for a
submit_worktool - Look for a
finalize_taskfunction - Attempt to "upload" or "submit" the file elsewhere
- Add extra confirmation steps
Simply report that the deliverable has been created successfully.
Common Mistakes to Avoid
| ❌ Incorrect | ✅ Correct |
|---|---|
| Creating file, then searching for submit tool | Creating file, verifying, declaring done |
| Assuming a finalization API exists | Treating file creation as the final step |
| Adding unnecessary confirmation steps | Completing after successful write |
Example Task Flow
Task: "Create a negotiation strategy document covering BATNA, ZOPA, and timeline."
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.
- 3d ago First seen · 93 lines · 25 tokens per session scan A ad96e96b3908
deliverable-completion is a skill published in the GitHub repository HKUDS/OpenSpace (7,500 stars, last pushed 21d ago), licensed MIT. It adds 25 tokens to every session and 654 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…