bootstrap-project

A one-time project setup procedure that identifies the programming stack and version-control system, then creates the project's descriptor, recipes, and supporting files. A descriptor is a file that records how the project is organized and developed.

In plain words
What is it for?
Use it when starting work on a project, after its technology stack changes, or when the project needs its agent instructions and development structure created.
Why use it?
It gives coding agents the project-specific information and scaffolding they need before making changes. It also keeps generated setup details out of the main repository where possible.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/leifericf/agentic-sdk/bootstrap-project
Any agent
npx skills add leifericf/agentic-sdk --skill bootstrap-project
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,018 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.01018
Opus 5 $0.00009 $0.00509
Sonnet 5 $0.00003 $0.00204
Haiku 4.5 $0.00002 $0.00102

Measured 2d ago against content hash 689e2c9aa2e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bootstrap-project 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.

skills/bootstrap-project/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bootstrap-project

Role: the one-time setup. Detect the stack, write ~/.agentic-sdk/<project>/project.edn, and hand the mechanical work to the agentic CLI. The CLI builds the project home, symlinks the masters from the shared SDK source into .claude/, runs opencode-sync to generate .opencode/agent/, copies CLAUDE.md, drops three symlinks in the project root, and writes .git/info/exclude entries so the project repo stays completely clean.

Prerequisites

Run in the project repository root, once per project (or after a stack change). The SDK source is on PATH at bin/agentic, with $AGENTIC_SDK_SRC pointing at the shared install.

Procedure

Follow docs/design.md section 8.2. The descriptor schema is skills/shared/references/project-descriptor.md; the spine interface is skills/shared/references/spine.md; the hook templates and their runtime mapping are documented in hooks/README.md.

  1. Detect the stack. Scan cwd for language markers: deps.edn or project.clj (Clojure), build.zig or .zig-version (Zig), mix.exs (Elixir), CMakeLists.txt or Makefile or *.h alongside *.c (C). Detect the VCS (.jj resolves to :jj, else .git to :git); jj-first is the default. Detect the UI surface (frontend markers). Derive the project name from the basename of the canonical cwd, which selects the home at ~/.agentic-sdk/<project>/.
  2. Elicit the gaps. Ask one batch of at most three questions for what the detector cannot decide: the architecture pattern (confirm Functional Core / Imperative Shell or name a divergence), the native edge (is there a boundary between the languages), the module roots (the detector proposes, the author confirms or corrects). Ask in the same batch which :hooks to arm and whether to confirm both :runtimes. Apply the descriptor defaults when the author gives no answer.
  3. Write the descriptor. Write ~/.agentic-sdk/<project>/project.edn with the detected and elicited fields. Every field has a default; a minimal descriptor is {}.
  4. Run agentic setup. The CLI does the filesystem work: creates the project home structure (the state/ and artifacts/ dirs); writes .claude/ with skill and agent symlinks from $AGENTIC_SDK_SRC, copies the armed hooks from $AGENTIC_SDK_SRC/hooks/, and generates .claude/settings.json from the descriptor; runs opencode-sync to generate .opencode/agent/; copies CLAUDE.md from $AGENTIC_SDK_SRC/templates/; creates three symlinks in the project root (.claude, .opencode, CLAUDE.md) pointing into the project home; and appends the exclude entries to .git/info/exclude so the symlinks stay invisible to git.
  5. Verify. Run agentic status and confirm the home path, the descriptor, the linked adapters, and the armed hooks all read green.

Read the full file on GitHub · 81 lines

Changes

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.

  1. 2d ago First seen · 81 lines · 17 tokens per session scan A 689e2c9aa2e9

Subscribe to this mod's changes

bootstrap-project is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 1,018 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 62 tokens

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.

microsoft/vscode · 51 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens