Agents Md Generator

AGENTS.md Generation Capability

This skill enables the agent to generate AGENTS.md files that serve as contributor guides for AI agents working on a codebase.

Core Capability

• Function: Analyze repository boundaries and generate or update a standardized AGENTS.md document
• Output Format: Markdown file with structured sections
• Character Limit: Dynamic, based on repository LOC (Lines of Code)
• Monorepo Support: Automatically detects monorepo structures and generates hierarchical documentation (Root + Packages)
• Update Support: Refreshes only standard sections in an existing AGENTS.md, preserving user-defined custom sections. Applies only to files generated by this skill; externally-authored AGENTS.md files are never modified

Output Sections

Single Repo / Package Document (4-5 Sections)

For single repositories or individual packages in a monorepo:

• Overview: 1-2 sentence project description (abstract, no tool/framework lists)
• Ownership Map: Optional, evidence-backed map split into stable ownership boundaries and active change routes — entry points, state owners, behavior decision points, external surfaces, contracts/side effects, verification anchors, and recent history-informed routes. Omit this section when the repository does not expose stable boundaries or active routes worth documenting; never invent ownership just to fill the template.
• Core Behaviors & Patterns: Cross-cutting patterns traced through full flows — error propagation chains, state lifecycle transitions, cross-boundary wiring mechanisms, resilience/recovery strategies, shared resource management. Discovered via multi-phase analysis: surface idiom detection, then deep tracing across layers.
• Conventions: Naming, code style, API/interface design conventions (callback naming, return value shapes, method responsibility splitting), configuration/registration structure, boundary conventions (error flattening, schema drift absorption, containment rules), component composition patterns.
• Working Agreements: Rules for agent behavior and communication

Monorepo Root Document (2-3 Sections)

For the root of a monorepo structure:

• Overview: 1-2 sentences describing the monorepo's purpose
• Ownership Map: Optional map split into stable package-level responsibility boundaries and active cross-package change routes. At monorepo roots, package names plus manifests, public exports, README text, dependency direction, and recent confirmed change clusters can establish enough evidence; omit the section when the root exposes only an uninformative package list.
• Working Agreements: Common working agreements applicable to all packages

Operation Modes

Generate vs Update

• Generate: Creates a new AGENTS.md from scratch (default when no AGENTS.md exists)
• Update: Refreshes standard sections in an existing AGENTS.md while preserving custom sections. Applies only to files generated by this skill — if no standard heading matches (the file was authored outside this skill), do not modify it; report to the user instead. See [./references/updatestrategy.md](./references/updatestrategy.md) for detailed workflow and section matching rules.

The agent automatically selects the appropriate mode based on whether an AGENTS.md file already exists at the target location.

Generation Modes (Monorepo)

Supports three modes: All (root + all packages, default), Root Only, and Single Package. See [./references/monorepostrategy.md](./references/monorepostrategy.md) for detailed strategy and mode selection criteria.

Execution Workflow

Run these steps in order. Each step has a fixed output that the next step depends on; skipping ahead produces wrong character budgets, unmatched update sections, or missed monorepo packages. The bundled scripts under ./scripts/ make the deterministic steps reproducible — invoke them rather than re-deriving the logic each run.

Step 1 — Decide Mode

1. Check whether AGENTS.md exists at the target location. Present → Update (subject to the skill-ownership check in Step 5). Absent → Generate.
2. Run monorepo detection at the repo root:

``bash python ./scripts/detect_monorepo.py ``

Output: {is_monorepo, markers}. A true result is provisional: discover the actual packages per [./references/monorepodetection.md](./references/monorepodetection.md). If fewer than 2 packages are found, treat the repo as a single document despite the marker. Otherwise choose All / Root Only / Single Package per [./references/monorepostrategy.md](./references/monorepostrategy.md). If is_monorepo is false, treat the repo as a single document.

Step 2 — Measure LOC and Allocate Budget

For each target document (single repo, or root + each package), run:

python ./scripts/loc_to_limit.py 

Output: {loc, scale, character_limit}. If the script reports tokei is missing, surface its install message and stop — do not estimate LOC by hand. Allocate character_limit across sections using the proportions in [./references/locmeasurement.md](./references/locmeasurement.md) (Section Budget Allocation).

Step 3 — Build Stack Context

Before pattern/convention analysis, read the package manifests at the document's scope (root or per package) per [./references/readonlycommands.md](./references/readonlycommands.md) > Dependency Discovery. Skip lock files. Use this stack context to focus Step 4 on relevant frameworks rather than searching blindly.

Step 4 — Analyze the Repository

For Update mode, use git history as an ownership-discovery signal before deep source tracing:

1. Prefer changes since the last skill-generated AGENTS.md update for the target document. If no reliable update anchor exists, default to roughly the last 3 months and adjust by repository activity.
2. Run the bundled high-churn signal helper before manually expanding git history:

``bash python ./scripts/git_ownership_signals.py ``

If a reliable update anchor exists, pass it with --anchor . The script emits compact Markdown-KV to minimize context use.

1. Start with commit metadata and changed paths only. Do not read broad diffs by default.
2. Look for changed-path clusters, repeated co-change patterns, renames/moves, deleted paths, and high-churn boundary files.
3. Use history to decide where to inspect next, not what to document. Add an Ownership Map boundary only when current code or documented contracts confirm it.
4. Do not persist timeline summaries such as "earlier focus" or "current focus" in AGENTS.md. Report them only in the user-facing summary unless the transition is currently represented in code as a live migration or compatibility boundary.

See [./references/readonlycommands.md#git-history-signals-update-mode](./references/readonlycommands.md#git-history-signals-update-mode) for token-safe git commands and expansion rules.

Run the multi-phase analysis defined in [./references/agentsmdtemplate.md](./references/agentsmdtemplate.md):

1. Phase 1 — Stack & Surface Discovery (recurring idioms in 3+ files, project-specific abstractions).
2. Phase 2 — Deep Tracing across layers (error propagation, wiring, state lifecycle, failure paths, centralized delegation).
3. Phase 3 — Validation (each pattern present in 3+ locations, accounting for cross-layer flows).

If Serena MCP is available, prefer its read-only symbol tools (find_symbol, find_referencing_symbols, get_symbols_overview, etc.) over rg / grep / find — symbolic queries are more accurate for caller tracing and cross-layer flows. See [./references/readonlycommands.md#symbol-level-analysis-optional-requires-serena-mcp](./references/readonlycommands.md#symbol-level-analysis-optional-requires-serena-mcp).

Run this analysis in the current context only. Do not delegate to subagents — Phase 3 cross-pattern validation and section-level budget tracking require a unified view (see [Scope Boundaries](#scope-boundaries) > Single-Context Execution).

Stay within each section's character budget from Step 2. Document only patterns/conventions actually observed.

If optional ## 2. Ownership Map has no evidence-backed content, omit the section and keep later section numbers unchanged. Section numbers are update-mode identifiers; never renumber Core Behaviors & Patterns, Conventions, or Working Agreements to close the gap. When evidence exists, split Ownership Map content into Stable Ownership Boundaries for the durable safety boundaries the previous single-list Ownership Map would have documented, and Active Change Routes for recent history-informed routes confirmed against current code. Treat Active Change Routes as additive update-mode context, not as a replacement or filter for stable boundaries. Stable bullets are full change-routing rules; Active bullets are parent-linked or cross-boundary delta routes. Do not restate the parent Stable boundary's broad owner, contract, or verification in Active. If no meaningful delta remains after removing inherited Stable details, omit the Active route. Do not impose a bullet-count limit beyond the section character budget.

Step 5 — Assemble (Generate) or Splice (Update)

• Generate: Emit the document using the structure in [./references/agentsmdtemplate.md](./references/agentsmdtemplate.md) (4-5 sections for single repo / package, 2-3 for monorepo root, depending on whether Ownership Map has evidence-backed content). Use [./references/workingagreements.md](./references/workingagreements.md) for the Working Agreements section.
• Update: Run the section parser on the existing file:

``bash python ./scripts/parse_sections.py --doc-type single_repo ``

(Use --doc-type monorepo_root for the monorepo root document.) The output marks each ## heading as is_standard (managed) or not (preserved), flags evidence-gated headings in optional_standard, and marks matched optional sections with is_optional_standard. Legacy ## 2. Folder Structure sections are also managed and report canonical_title: "## 2. Ownership Map" so update mode can migrate old generated files. Replace only the standard sections' bodies; keep custom sections, the file title, and any preamble before the first ## unchanged. Insert any missing_standard heading at its numbered position relative to other standard sections only when the section is required or has evidence-backed content. Full reassembly rules: [./references/updatestrategy.md](./references/updatestrategy.md).

Skill-ownership check: if the parser output contains zero is_standard: true sections, the existing AGENTS.md was not generated by this skill. Do not modify it — report this to the user and stop. Proceed with full regeneration only on their explicit request.

If the existing document type no longer matches the repo (e.g., a single repo became a monorepo), force full regeneration instead of update: carry every custom section over verbatim into the regenerated document (original order preserved) and get the user's confirmation before overwriting.

Step 6 — Verify and Write

Before writing, confirm:

• The combined length of the preamble and the standard (managed) sections is within character_limit; no standard section exceeds its budget. Custom sections are excluded from the budget and must never be trimmed to satisfy it.
• None of the [Anti-Patterns](./references/agentsmdtemplate.md#anti-patterns-excluded-content) appear (no Common Commands, run/test/build/deploy instructions, IDE/tooling settings, etc.). Exception: the discovered type-check command in Working Agreements is required content, not a build/run instruction.
• For Update mode: every standard section body was rebuilt from its managed source, not reused because the old wording appeared acceptable.
• For Update mode: scan only managed standard sections for stale standing work-agreement wording. Fail verification if managed content still contains Keep edits minimal, Minimal changes, preserve public APIs, existing plugin behavior, or avoid unnecessary abstraction; custom sections may keep any user-owned wording.
• For Update mode: every preserved custom section is byte-for-byte identical to the original.
• For Update mode: report to the user any wording being removed from managed standard sections — user additions inside managed sections are not preserved, so list what is dropped before overwriting and suggest moving anything user-owned into a custom section.
• For Update mode: if an existing managed Ownership Map or legacy Folder Structure section will be omitted because no current evidence supports it, report that whole-section removal and get confirmation before overwriting.
• For single-repo documents: the managed Working Agreements section does not contain monorepo-only wording such as package-level AGENTS.md guidance.

Then write with the Edit/Write tool. For Monorepo with mode = All, repeat Steps 2–6 per target package after handling the root, re-running the Step 1 Generate/Update decision (and the skill-ownership check) for each package — a package without AGENTS.md is Generate even when the root was Update.

Tools

This skill uses the following read-only tools for repository analysis. See [./references/readonlycommands.md](./references/readonlycommands.md) for detailed usage patterns.

• Serena MCP symbol tools (preferred when available): find_symbol, find_referencing_symbols, find_referencing_code_snippets, get_symbols_overview, search_for_pattern, list_dir, find_file, read_file. Prefer these over rg / grep / find for symbol lookups, caller tracing, and structural analysis. Use only the read-only tools listed; do NOT invoke write/edit symbol tools or execute_shell_command. See [./references/readonlycommands.md#symbol-level-analysis-optional-requires-serena-mcp](./references/readonlycommands.md#symbol-level-analysis-optional-requires-serena-mcp).
• tokei: LOC measurement (required)
• rg (ripgrep): Content search (fallback when Serena MCP is unavailable)
• grep / Select-String: Content search (fallback per OS, when neither Serena nor rg is available)
• sed -n / Get-Content \| Select-Object: Paginated file reading per OS
• tree: Directory structure visualization
• find: File and directory discovery (Linux / macOS, fallback when Serena find_file is unavailable)
• ls, pwd: Basic directory navigation
• git log, git show --stat, git show --name-only: Update-mode ownership discovery signals; use the bundled script first, then metadata and changed paths, never broad diffs by default

Bundled Scripts

Deterministic steps are bundled as scripts under ./scripts/ so they run identically across invocations and platforms. Prefer these over re-deriving the logic in natural language.

• scripts/loc_to_limit.py: Runs tokei with the prescribed exclusions, parses the Total row, and returns {loc, scale, character_limit}. Surfaces the install message and exits non-zero if tokei is missing.
• scripts/detect_monorepo.py: Checks marker files (pnpm-workspace.yaml, lerna.json, nx.json, turbo.json, rush.json, .moon/workspace.yml, go.work, Cargo.toml [workspace] members, package.json workspaces, Gradle settings.gradle*, Maven pom.xml , Bazel, Buck2, Pants, Hatch/uv/rye). Matching is comment- and JSON-aware. Returns {is_monorepo, markers}; a true result is provisional until package discovery finds 2+ packages (Step 1).
• scripts/parse_sections.py: For Update mode. Parses an existing AGENTS.md and returns a section map flagging which ## headings are standard (managed) vs custom (preserved), plus any missing standard headings. Headings inside fenced code blocks are ignored.
• **`scripts/git_ownership

…

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: buYoung
• Source: buYoung/skills
• License: MIT

Install and usage instructions live in the source repository linked above.