# Repo Bootstrapper > Generates and maintains the full mdb-tam file standard for any repository. Parent: [Developer Tooling & Repo Automation](https://llms-explorer.com/tree/developer-tooling-repo-automation/) · 25 facets · 104 facts · page: https://llms-explorer.com/tree/repo-bootstrapper/ ## Repo Bootstrapper & Standards Maintainer - Generates and maintains the full mdb-tam file standard for any repository. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#repo-bootstrapper-standards-maintainer) ## When to use this skill - Create an ideal repository from scratch using the full mdb-tam standard (includes code quality optimization and LLM doc generation) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Upgrade an existing repository toward that same ideal state (runs cdo and crawl-repo-to-llms automatically) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Initialize a brand-new repository to the mdb-tam documentation and workflow standard — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Audit an existing repo against the standard and fill any gaps — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Update stale documentation sections (architecture, commands, known-issues, etc.) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Create or update the docs/ suite, memory.md, prompts.md, CLAUDE.md, .github/copilot-instructions.md — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Keep docs/high_signal_file_index.json and docs/codebase-overview.md current after large changes (regenerated by crawl-repo-to-llms) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) - Optimize code quality and generate LLM-friendly documentation as part of standard repo modernization — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-to-use-this-skill) ## When NOT to use this skill - Pure code review or bug hunting - use the /code-review command — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - Pure security audit - use security-reviewer — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - Code-pattern extraction without meta-doc work - use repo-pattern-scanner — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - Production-log / runtime-error triage - review prod logs, root-cause a live error, verify a fix, open a remediation PR → the error-monitor-remediator agent (rule book: docs/error-monitoring-guide.md). This skill is a static meta-doc/standards maintainer with no telemetry access; it audits whether logging and test docs meet the standard, it does not read production logs or open PRs from runtime errors. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - Repo not following mdb-tam conventions - surface what the standard would require and ask before writing — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - Read-only or locked repo - report findings only; do not write any files — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) - No clean working tree - verify git status is clean or operator has acknowledged the risk before writing — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#when-not-to-use-this-skill) ## Entry point - Input: expects a local git repository path (absolute or CWD). If not a git repo, stop and report. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#entry-point) - Bootstrap prompt fallback: if mdb-tam/docs/repo-bootstrap-prompt.md cannot be loaded, stop and ask for the path to the local mdb-tam checkout. Do not proceed with run_bootstrap or create_ideal_repo without it. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#entry-point) - Top-level output after any write phase: — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#entry-point) ## Skill guidance - This skill's canonical bootstrap prompt lives in mdb-tam at docs/repo-bootstrap-prompt.md. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - When auditing, check each file in the Standard File Manifest below. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Read the audit ledger first. Before any new audit, read existing docs/repo-bootstrap-audit-*.md files. Never re-raise a finding marked RETRACTED there without new evidence - fresh LLM passes reliably re-discover plausible-but-wrong findings (e.g. demanding DATASTORE_VERIFY_FAILED on kind: check/report ops when the gate only applies to kind: sync). — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Verify subagent findings against the artifact before acting. Parallel audit agents over-report: "row has missing-coverage marks" gets reported as "call is undocumented", and per-block entry counts get reported as totals. Grep/read the target yourself before writing a remediation. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Always infer from the actual codebase - never invent commands or paths. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Full rewrites are appropriate when they materially improve clarity and maintainability. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Use parallel agents for independent work phases: file-manifest audit, external-call inventory, extended checks, and skill-coverage gap analysis can all run concurrently. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - Never write real credentials, tokens, API keys, or env var values into any generated file. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) - .env / .env.example may be read+write denied by Claude Code permission settings. Fall back to grep -rE "process\.env\.[A-Z_]+" for the var inventory and emit the missing-var list as a copy-paste TODO block instead of editing the file. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#skill-guidance) ## Standard File Manifest - Every repo that meets this standard must have ALL of the following files. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#standard-file-manifest) ## Operations Infrastructure - Auto-remediation contract: a repo passes the audit only when every external call in docs/external-calls.md satisfies all five standards (CLI trigger, centralized error log, auto-remediation map, dashboard card, datastore verification). See references/coding-standards.md for full requirements. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#operations-infrastructure) ## Audit - The detailed per-file audit checklist lives in references/audit-checklist.md. Run it against every file in the manifest. Severity rubric: blocking, major, medium, minor. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#audit) ## Auto-remediation workflow - When the audit finds gaps, update_to_ideal_repo runs these passes in order: — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - Drift pass - compare every manifest file against current state; update commands, paths, versions, agent inventories; drop sections that no longer apply. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - External-call inventory pass - grep for every external call, populate docs/external-calls.md, emit a per-call task for each missing standard. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - Code quality pass - run code-deep-optimizer (cdo) to audit source code for bugs, efficiency, and maintainability; apply all Medium+ findings automatically. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - LLM documentation pass - run crawl-repo-to-llms to generate machine-readable LLM-friendly documentation indexes (docs/high_signal_file_index.json, llms.txt metadata, semantic embeddings). — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - Convergence loop - re-run the drift pass after each change set. Stop when the audit returns zero medium-or-higher findings. Hard cap: 3 iterations. After 3, surface remaining findings as a TODO list and stop. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - Repo hygiene pass - commit all changes, stage untracked files, clean up dangling work, and leave repo in a clean state with no shadow branches or uncommitted changes. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - Hub registration pass - register or update the project in ~/.global-ai-hub project registry; sync metadata (paths, tags, languages, description) if already registered. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) - No-invention rule - never fabricate a command, path, env var, or external service. Surface unknowns as TODO with where-to-find. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#auto-remediation-workflow) ## `audit_repo(path)` → gap report - Run the audit checklist from references/audit-checklist.md against all files in path. Produce: — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#audit_repopath-gap-report) ## `update_file(file, repo_context)` → updated file content - Read the current content — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_filefile-repo_context-updated-file-content) - Read relevant source files in the codebase — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_filefile-repo_context-updated-file-content) - Extend, restructure, or fully rewrite to meet the ideal repo standard while preserving correct repo-specific facts — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_filefile-repo_context-updated-file-content) ## `create_ideal_repo(path)` → ideal repo baseline - Read the repo and identify canonical version file, runtime model, commands, docs, integration boundaries — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Create the full standard file manifest — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Rewrite weak top-level docs so the repo has a clear entry point, workflow rules, and maintenance baseline — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Run code-deep-optimizer (cdo) to audit and optimize source code from the start — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Run crawl-repo-to-llms to generate LLM-friendly documentation and semantic indexes for the new repo — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Repo hygiene & commit - stage all new files, commit bootstrap changes, ensure clean working tree — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) - Hub registration - register project in ~/.global-ai-hub registry with metadata (path, languages, tags, description) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_ideal_repopath-ideal-repo-baseline) ## `update_to_ideal_repo(path)` → modernization plan + execution - Check git status - stop and ask if working tree is dirty and operator has not acknowledged the risk — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Audit every standard file for correctness, completeness, and clarity — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Upgrade stale docs, indexes, workflow files, and skills — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Run code-deep-optimizer (cdo) to audit and fix source code - auto-applies all Medium+ findings — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Run crawl-repo-to-llms to generate LLM-friendly documentation indexes and semantic metadata — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Re-run audit after code and doc passes to validate no regressions — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Repo hygiene & commit - stage all untracked files, commit all changes (with descriptive message), clean up any shadow branches or dangling work, ensure clean git status — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Hub registration - register or update project in ~/.global-ai-hub registry; sync repo metadata (paths, tags, languages, description) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) - Prefer clean rewrites over incremental patching when a file has duplication, drift, or low-signal structure — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#update_to_ideal_repopath-modernization-plan-execution) ## `create_operations_registry(path)` → operations-registry.js + MCP tools + tests + CI check - Grep for every external call (fetch, http.request, execFile, exec, spawn, child_process, fs.watch, SDK client calls) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Extract: file:line, target, transport type, error handling, retry logic — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Generate server/src/lib/operations-registry.js with one OperationEntry per call — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Generate buildToolInventory() and writeToolInventory() functions — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Generate scripts/generate-ops-registry-doc.mjs as the sole writer of docs/operations-registry.json; add ops:doc and ops:doc:check npm scripts to package.json — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Register MCP tools: tam_ops_list, tam_ops_get, tam_ops_run, tam_ops_history, tam_ops_status, tam_ops_audit, tam_ops_remediation, tam_ops_write_doc, tam_tool_inventory, tam_write_tool_inventory — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Add tests and CI drift check (ops:doc:check step in .github/workflows/ci.yml) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) - Update docs/external-calls.md and docs/tool-inventory.json — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_operations_registrypath-operations-registryjs-mcp-tools-tests-ci-check) ## `create_skill_for_context(context_file_path)` → SKILL.md + .skillfish.json - Produce both skill files following the format in Phase 6 of the bootstrap prompt (loaded from mdb-tam/docs/repo-bootstrap-prompt.md). — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#create_skill_for_contextcontext_file_path-skillmd-skillfishjson) ## `sync_memory(version, completed_items, next_steps)` → memory.md entry - Produce a new versioned entry for memory.md in the correct format. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#sync_memoryversion-completed_items-next_steps-memorymd-entry) ## `cleanup_and_commit(path)` → clean repo state - Get the repo current - pull latest from remote if applicable — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) - Stage all untracked files in the repo — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) - Commit all uncommitted changes with a descriptive message (format: "repo: modernization & cleanup" or similar) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) - Identify and clean up any shadow branches or dangling work (stashed changes, detached HEAD, leftover branches) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) - Verify git status returns clean - no uncommitted changes, no untracked files — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) - Report final state: commit shas, branches cleaned, files committed — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#cleanup_and_commitpath-clean-repo-state) ## `register_with_hub(path)` → hub registry entry - Check if project exists in ~/.global-ai-hub/registry.json (or equivalent project manager) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#register_with_hubpath-hub-registry-entry) - If NOT registered: create new entry with metadata (absolute path, project name, languages, primary tags from package.json/docs, description from README) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#register_with_hubpath-hub-registry-entry) - If already registered: update metadata (sync paths, update tags, refresh description, update last-modified timestamp) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#register_with_hubpath-hub-registry-entry) - Validate entry against hub schema — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#register_with_hubpath-hub-registry-entry) - Write/update registry and report final state: entry ID, metadata synced, timestamp — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#register_with_hubpath-hub-registry-entry) ## `run_bootstrap(repo_path)` → full task prompt - Load docs/repo-bootstrap-prompt.md from mdb-tam (not from the target repo) — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#run_bootstraprepo_path-full-task-prompt) - Substitute the actual repo_path, current branch name, and current HEAD sha into the prompt — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#run_bootstraprepo_path-full-task-prompt) - Return the full customized prompt for the operator to run — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#run_bootstraprepo_path-full-task-prompt) ## Bundled Context - The full bootstrap prompt lives at docs/repo-bootstrap-prompt.md in mdb-tam. Load it when the user asks to initialize, modernize, or turn a repository into an ideal repo. Do not hard-code local filesystem paths - resolve the file at runtime from the mdb-tam checkout on the current machine. — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#bundled-context) ## References - Full per-file audit checklist: references/audit-checklist.md — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#references) - 5-standard coding requirements for external calls: references/coding-standards.md — [source](https://llms-explorer.com/sources/mdb-context-hub/repo-bootstrapper/#references) ## Where this helps - Bringing a repository missing standard meta-documentation — CLAUDE.md, README, CI config, issue templates — up to a consistent baseline in one pass instead of recreating each file by hand. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Auditing an existing repo against a standard file manifest to see exactly which expected files, docs, or operations infrastructure are missing before a larger cleanup. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Onboarding a new repository into an organization's conventions — CODEOWNERS, dependabot, CI workflows — without hand-copying boilerplate from another repo. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Generating an operations registry and tool inventory for a repo so its automation surface — scripts, CLI commands, env vars — is documented and discoverable. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Running a scheduled or triggered re-bootstrap pass after a repo has drifted from standard, such as new files added without matching docs or stale CI config. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* ## Project ideas - Run the audit step against several existing repos and compare the gap reports to prioritize which ones need bootstrapping first. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Wire the auto-remediation workflow into a repo's CI so drift from the standard file manifest is flagged automatically on every PR. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Extend the standard file manifest with an org-specific file, such as a security-policy template, and re-run bootstrap across a repo fleet to roll it out everywhere at once. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Build a small dashboard summarizing bootstrap and audit results across every repo a team owns, so gaps are visible at a glance instead of repo-by-repo. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* ## Antipatterns - Running the bootstrapper once and never re-auditing, so a repo drifts back out of standard as new files and conventions get added without matching updates. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Blindly accepting every auto-remediation suggestion without reviewing the diff, especially for files like CI workflows whose behavior directly affects builds and deploys. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Bootstrapping a repo that intentionally deviates from the standard without first checking the "when NOT to use this skill" guidance, then fighting the tool's assumptions afterward. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Treating the generated operations registry and file manifest as static once created instead of keeping them in sync as the repo's actual scripts and tooling evolve. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* ## Known issues - The standard file manifest assumes a particular org convention; repos with genuinely different structure or governance needs may need manual adjustment after bootstrapping rather than accepting the defaults wholesale. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Auto-remediation can regenerate a file a maintainer had deliberately customized, overwriting intentional deviations if the tool isn't told to preserve them. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Registering a repo with the hub and creating an operations registry both assume specific downstream tooling — MCP tools, CI check integration — is present; running bootstrap without it leaves some steps incomplete. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* - Because this operates on a whole repo, running it against a very large or unusual monorepo layout can surface edge cases the standard manifest and audit logic weren't designed around. — [source](https://llms-explorer.com/tree/repo-bootstrapper/) *(AI-suggested, synthesized from this pack's existing facts — not extracted from a source document.)* ## Context files - [Repo Bootstrapper](https://llms-explorer.com/downloads/sources/mdb-context-hub/repo-bootstrapper.md)