warmup
Warm up a fresh Claude/Codex session by loading repo-local context.
Skill by tcbuilds
Chalk Labs
Need help deploying warmup?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tcbuilds-warmup
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/warmup
What's inside
- Skill name
warmup- Description
- Warm up a fresh Claude/Codex session by loading repo-local context. Use when starting work in an existing repo, "warm up", "get context", "catch up", "load project", or "what have we been working on". Summarizes rules, recent git history, current state, and likely next steps.
- License
- MIT
- Instructions
- 110 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Session Warmup Quickly load enough repository context to work safely without rereading the whole repo. Keep output concise: orientation, current state, risks, and next actions. ## When to invoke Use at the start of a fresh session, after switching repositories, after context compaction, before planning work in an unfamiliar repo, or before resuming a paused implementation. ## Process ### 1. Read repo-local instructions Read any present files: - `AGENTS.md` - `CLAUDE.md` - `README.md` - `CONTRIBUTING.md` - `SECURITY.md` - `.claude/rules/standards.md` and matching path-scoped `.claude/rules/**/*.md` - `.claude/` - `docs/` Repo-local instructions override global defaults. Do not paste secrets or controlled data from these files into the summary. ### 2. Read handoff and plan docs Read any present files: - `HANDOFF.md` - `handoff.md` - `implementation_plan.md` - `repo_orientation.md` - `CHANGELOG.md` - recent ADRs under `docs/adr/` or `adr/` Capture current resume point, blockers, open decisions, and planned next task. ### 3. Inspect recent history and state Use compact commands: ```bash git branch --show-current git status --short git log --oneline --stat -15 git stash list ``` If the repo is GitLab-hosted, use merge request/pipeline terminology. If GitHub-hosted, use pull request/Actions terminology. If unknown, use platform-neutral language. ### 4. Identify repo shape Briefly identify: - main language/framework/runtime - package/build files - test commands if documented - CI/CD platform - deploy/runtime hints - sensitive-data or compliance-relevant areas Do not run installs, tests, builds, network calls, or write files during warmup unless the user explicitly asks. ## Output Return this structure: ```markdown ## Session Context Loaded **Project:** <name or directory> **Branch:** <branch> **Status:** clean / uncommitted changes / stashed work / unknown **Platform:** GitLab / GitHub / other / unknown ### Repo Rules - <key repo-local rules> ### Recent Activity - <theme from recent commits> - <files or areas touched> ### Current Work Surface - <likely active task or area> - <relevant docs/plans/handoff notes> ### Commands Found - Setup: <command or Not documented> - Test: <command or Not documented> - Build: <command or Not documented> - Deploy: <command or Not documented> ### Risks / Gaps - <uncommitted changes, missing docs, unclear deploy path, sensitive data, failing tests, etc.> ### Ready Next - <1-3 concrete next actions> ``` ## Guardrails - Evidence first. Do not invent commands, deployment paths, or project purpose. - Keep summary short enough to be useful in the main context. - Flag uncommitted changes and stash entries. - Do not expose secrets, controlled data, customer names, internal hostnames, or raw environment values. - Do not modify files during warmup. - If repo instructions conflict, report the conflict and follow the most local file.
From tcbuilds/nautilus, MIT.
More from tcbuilds/nautilus
- 0.570score
prompt-injection-audit
tcbuilds
Run a read-only, evidence-based audit of an LLM or agent application for prompt injection and the failures that make injection matter.
SkillAFreshness: AClaude Code +9 - 0.566score
codex-implement
tcbuilds
Execute one implementation slice or an implementation_plan.md task, phase, or full plan through parallel file-owned Codex CLI workers in isolated Git worktrees.
SkillAFreshness: AClaude Code +9 - 0.565score
codex-review
tcbuilds
Run a second-pass Codex review over changed files, produce severity-ordered findings, and escalate repeated fix-loop invariants to a Sol-max repair architect.
SkillAFreshness: AClaude Code +9 - 0.529score
pi-implement
tcbuilds
Execute one implementation slice or an implementation_plan.md task, phase, or full plan through Pi-native subagent workflows.
SkillBFreshness: BClaude Code +9 - 0.524score
repo-orientation
tcbuilds
Build an onboarding-quality breakdown of an existing repository.
SkillBFreshness: BClaude Code +9 - 0.524score
pi-review
tcbuilds
Run an independent Pi-native review over changed files using fresh-context reviewer subagents, evidence-backed severity findings, parent synthesis…
SkillBFreshness: BClaude Code +9 - 0.524score
roadmap
tcbuilds
Create or update implementation_plan.md with the smallest evidence-backed set of Markdown task checkboxes that fully satisfies the request.
SkillBFreshness: BClaude Code +9 - 0.520score
claude-build
tcbuilds
Claude Code-only implementation workflow for implementation_plan.md using Claude specialist agents, phase-boundary commits, and the codex-review gate.
SkillBFreshness: BClaude Code +9 - 0.494score
bro
tcbuilds
Restate the last message in plain human language, with no jargon.
SkillBFreshness: BClaude Code +9 - 0.479score
nautilus-sync
tcbuilds
Sync a personal skill or agent from ~/.claude/ into a public-facing nautilus-shaped playbook repo as a sanitized loadable artifact.
SkillCFreshness: CClaude Code +9 - 0.474score
handoff
tcbuilds
Capture the state of an in-flight session into HANDOFF.md so a future session, teammate, or agent can resume without re-deriving context.
SkillCFreshness: CClaude Code +9 - 0.474score
refine-spec
tcbuilds
Read a draft spec file (idea.md, mvp.md, prd.md, brief.md, plan.md, spec.md, etc.) and interactively quiz the user across multiple rounds with AskUserQuestion…
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 11, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tcbuilds/nautilus
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tcbuilds
- 0.570score
prompt-injection-audit
tcbuilds
Run a read-only, evidence-based audit of an LLM or agent application for prompt injection and the failures that make injection matter.
SkillAFreshness: AClaude Code +9 - 0.566score
codex-implement
tcbuilds
Execute one implementation slice or an implementation_plan.md task, phase, or full plan through parallel file-owned Codex CLI workers in isolated Git worktrees.
SkillAFreshness: AClaude Code +9 - 0.565score
codex-review
tcbuilds
Run a second-pass Codex review over changed files, produce severity-ordered findings, and escalate repeated fix-loop invariants to a Sol-max repair architect.
SkillAFreshness: AClaude Code +9 - 0.529score
pi-implement
tcbuilds
Execute one implementation slice or an implementation_plan.md task, phase, or full plan through Pi-native subagent workflows.
SkillBFreshness: BClaude Code +9 - 0.524score
pi-review
tcbuilds
Run an independent Pi-native review over changed files using fresh-context reviewer subagents, evidence-backed severity findings, parent synthesis…
SkillBFreshness: BClaude Code +9 - 0.524score
repo-orientation
tcbuilds
Build an onboarding-quality breakdown of an existing repository.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get warmup running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
warmup skill. Agent Mart. https://agentmart.dev/skills/tcbuilds-warmup (last updated 2026-10-24)