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/zhyx12/projtool/projtool-bootstrapnpx skills add zhyx12/projtool --skill projtool-bootstrapgit clone --depth 1 https://github.com/zhyx12/projtoolWhat 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 | $0.00168 | $0.01840 |
| Opus 5 | $0.00084 | $0.00920 |
| Sonnet 5 | $0.00034 | $0.00368 |
| Haiku 4.5 | $0.00017 | $0.00184 |
Grade A, and why
projtool-bootstrap 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
projtool-bootstrap
This skill activates the first time a user wants to bring a project under projtool. It is intentionally narrow: the user must mention projtool by name or use a clearly-projtool verb such as retrofit, install, set up, or onboard.
When You Should Not Act
- The project already has
.claude/skills/ml-research-workflow/; that project-level skill owns day-to-day projtool work. - The user is asking about agent/client skills in general, not projtool.
- The user is discussing ML workflow but has not asked to use projtool.
Main Flow
The full flow is in references/retrofit-flow.md. Follow that file, and trust
the live MCP tool schema over this document if they ever disagree.
Briefly:
- Check MCP availability.
mcp__projtool__detect_project_structureshould be callable. If not, tell the user to runprojtool setuponce from a shell and restart the active MCP client in this directory. - Detect. Call
mcp__projtool__detect_project_structureand summarize the detected train script, config directory, invocation style, package manager, data path hint, git state, and docs repo status. - Negotiate v4 config. Build a
ProposedConfigusing the v4 schema:paths.code_dir,main_worktree_name,data_dir,docs_dir,output_dir,remote_workspace,outputs_remote,data_remote, pluspaths.docs_repo_url. Do not use removed v3 fields such asdocs_repo_pathoroutputs_local. - Write templates. Call
mcp__projtool__retrofit_write_templatewith the agreed config. Surface conflicts and warnings exactly; do not claim success if conflicts remain. - Tell the user what changed. The raw git repo is converted into a v4
container layout:
code/main/holds the git worktree, while.proj-tool/,.claude/,.codex/,docs/,data/, andoutput/live at container root. - Hand off — executably, not rhetorically. The project-level
ml-research-workflowskill (just written to.claude/skills/) owns experiments, image builds, training, reports, and sync work from here.retrofit_write_templatereturnsnext_action+readiness— follow them:- If the user's ORIGINAL request continues into training / reproduction
("接入 projtool 并复现...", "set up projtool and run..."), attempt to
load the
ml-research-workflowskill NOW and continue the work there in the same session. - If this session cannot load a freshly-written project skill, say so
explicitly and tell the user to restart the session before any remote
work. NEVER continue with raw
remote_exec/ SSH clone / tmux — that is how projects end up with zero tracked runs (the weavetime failure mode). - First reproduction belongs on upstream main:
instance_up("main")→sync_now("main")→run_script(experiment_id="main", ...)(orrun_script(experiment_id="exp-<topic>", worktree="main")for a semantic run identity).new_experimentis for branching real research work, not for getting a sync session.
- If the user's ORIGINAL request continues into training / reproduction
("接入 projtool 并复现...", "set up projtool and run..."), attempt to
load the
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.
- 2d ago First seen · 141 lines · 168 tokens per session scan A 0ba5fd001251
projtool-bootstrap is a skill published in the GitHub repository zhyx12/projtool (1 stars, last pushed 19d ago), licensed MIT. It adds 168 tokens to every session and 1,840 once invoked, about $0.0008 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…