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/waltstephen/argusbot/final-task-reportnpx skills add waltstephen/ArgusBot --skill final-task-reportgit clone --depth 1 https://github.com/waltstephen/ArgusBotWrote 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/waltstephen/argusbot/final-task-report)<a href="https://agentmods.dev/skills/waltstephen/argusbot/final-task-report"><img src="https://agentmods.dev/badge/skills/waltstephen/argusbot/final-task-report.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.00592 |
| Opus 5 | $0.00024 | $0.00296 |
| Sonnet 5 | $0.00010 | $0.00118 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
final-task-report 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 4d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Final Task Report
Use this skill only in the final handoff phase.
Goal
Produce one Markdown report file that a user can read directly on phone or desktop.
The report must stay grounded in the actual work completed in the repository and current session. Do not invent experiments, datasets, or code changes.
This skill is meant to be updated over time as the reporting format evolves. Main agent should follow this skill directly for final report generation.
Required Sections
Always include these sections in order:
## 0. Original User Taskor## 0. 原始用户任务## 1. What This Task Proposedor## 1. 本次实验提出了哪些点## 2. How It Was Done and What Data Was Usedor## 2. 具体是怎么做的,使用了什么数据## 3. What the Main Agent Changed, What Approach It Used, and What Experiments It Ranor## 3. main agent 修改了什么,使用了什么思路,跑了什么实验## 4. Special Notesor## 4. 特殊说明
If the task context is mixed-language, bilingual section titles are acceptable.
Content Rules
- Summarize only completed work.
- If no dataset was used, write
未使用ornone. - If no experiment was run, write
未运行额外实验ornone. - Include the original user task and any explicit user follow-up requirements.
- Special Notes should capture:
- maintenance rules
- user-visible caveats
- follow-up constraints
- any special thing the user explicitly asked to be highlighted
- Do not infer or mention unrelated internal skill context. User requirements are enough.
- Prefer the language of the user task:
- Chinese task -> Chinese report
- English task -> English report
- mixed context -> bilingual or mixed headings
- Prefer concrete evidence:
- files changed
- commands/checks run
- observed outputs
- validation results
- Keep it readable on mobile:
- short paragraphs
- flat bullets
- avoid long walls of text
Write Contract
- Write to the exact file path requested by the caller.
- Do not rename the output file.
- Do not create multiple alternative reports unless explicitly requested.
- After writing, reply only with the final file path/status if the caller asks for a terse machine-readable response.
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.
- 4d ago First seen · 64 lines · 48 tokens per session scan A 77862b9cbc71
final-task-report is a skill published in the GitHub repository waltstephen/ArgusBot (316 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 592 once invoked, about $0.0002 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…