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/mblode/ghostwriter/train-ghostwriternpx skills add mblode/ghostwriter --skill train-ghostwritergit clone --depth 1 https://github.com/mblode/ghostwriterWhat 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 | $0.00076 | $0.02374 |
| Opus 5 | $0.00038 | $0.01187 |
| Sonnet 5 | $0.00015 | $0.00475 |
| Haiku 4.5 | $0.00008 | $0.00237 |
Grade A, and why
train-ghostwriter 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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Train Ghostwriter
Turn explicitly selected local writing into a private profile and uncontaminated evaluation set.
- IS: the only ghostwriter workflow that creates corpus files, profiles, cases, or references.
- IS NOT: a live connector, scraper, drafting skill, evaluator, continuous learner, or hosted data service. Use
ghostwriterto draft andevaluate-ghostwriterto evaluate.
Reference files
| File | Read when |
|---|---|
| references/corpus-contract.md | Always, before normalizing or validating samples. |
| assets/profile-template.md | The runner reads this during profile generation; read it when reviewing profile output. |
Workflow
Copy this checklist and track progress:
- 1. Establish the data root, sources, and platforms; explain the provider boundary.
- 2. Normalize samples into one JSONL staging file per the corpus contract.
- 3. Prepare the corpus: dry-run, review the split, then execute.
- 4. Generate and install one profile per platform through a clean session.
- 5. Prepare held-out evaluation cases, one clean session per ID.
- 6. Verify every script printed successful JSON with destinations, counts, and backups.
1. Establish the boundary
Resolve the data root from non-empty GHOSTWRITER_HOME, otherwise use ~/.config/ghostwriter. Ask for explicit source paths and a platform for each source. Do not search mailboxes, chats, home directories, or cloud services.
Resolve the absolute directory containing this SKILL.md once as the task-specific shell variable TRAIN_GHOSTWRITER_DIR. Invoke bundled scripts through that directory so the workflow works from an individual skill install or a repository checkout.
Explain before model use: source files remain on disk, but the writing included in a generation prompt is sent by the selected local CLI to its model provider. The repository adds no telemetry or network client.
Codex disables shell, apps, multi-agent, image generation, web search, and ambient skill instructions. It still registers update_plan, request_user_input, apply_patch, and view_image. Read-only mode blocks patch writes, the prompt prohibits every tool and local-file read, and local image paths are rejected before generation. Claude Code runs with no tools.
What ships with it
4 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.
- 2d ago First seen · 144 lines · 76 tokens per session scan A 4a6be122c813
train-ghostwriter is a skill published in the GitHub repository mblode/ghostwriter (7 stars, last pushed 27d ago), licensed MIT. It adds 76 tokens to every session and 2,374 once invoked, about $0.0004 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 2026-08-31.
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…