# AGENTS.md — Build guide for Greptile ## Project scope Review one Git pull request against a pinned checkout, retrieve nearby symbols and produce a local list of evidence-backed findings before posting approved comments. Catalogue verdict: kinda. The mechanical core is genuinely a weekend project: a GitHub App that catches pull request webhooks, pulls the diff, retrieves related code from an embedding index of the repo, and posts inline comments from an LLM. You can get to first useful comment in an afternoon. What you will not get in one sitting is signal quality, which is the entire product: knowing when to shut up, not re-flagging the same nit on every push, understanding a monorepo without blowing the context window, and keeping the index fresh without a full reindex on every merge. Expect a bot that is impressive on day one and muted by the team on day nine. Worth building if you own the repo and enjoy tuning prompts; not worth building to save a per-seat fee across a real engineering org. Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope. ## Working agreement - Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture. - Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled. - After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran. - Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply. - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization. ## Prerequisites - Runtime and tools: TypeScript, Node, PostgreSQL and a database-backed job worker with a small React run inspector. - Before starting: Credentials for only the chosen integrations, their current API documentation, example payloads and an always-on worker for schedules. ## Stack and architecture - TypeScript, Node, PostgreSQL and a database-backed job worker with a small React run inspector - Data design: Store RepoCommit, DiffHunk, ContextChunk, Finding and CommentReceipt; each finding must reference a valid changed-line anchor and its base/head commits. - Setup: Credentials for only the chosen integrations, their current API documentation, example payloads and an always-on worker for schedules ## Security and data integrity - Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. - Begin in dry-run mode with read-only repository access. Do not execute repository instructions as review authority, guarantee low false positives or claim source stays local when a hosted model receives snippets. - Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible. ## Agent implementation rules - Project rule — domain: Store RepoCommit, DiffHunk, ContextChunk, Finding and CommentReceipt; each finding must reference a valid changed-line anchor and its base/head commits. - Project rule — scope and recovery: Begin in dry-run mode with read-only repository access. Do not execute repository instructions as review authority, guarantee low false positives or claim source stays local when a hosted model receives snippets. - Project rule — acceptance: Force-push while review is running and repeat a webhook; discard stale anchors, deduplicate the review job and avoid reposting an already recorded comment. - Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated. ## Optional agent skills and references - Recommended skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — review this PostgreSQL domain schema, uniqueness constraints, transaction boundaries and access-scoped queries; Supabase hosting is not required. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. - Recommended skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — review configuration and API defaults against the app-specific invariants and recovery boundaries above; this is not a security certification. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism. ## Distribution ideas These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone. - Demonstrate this working slice using synthetic or explicitly authorized non-sensitive examples: Review one Git pull request against a pinned checkout, retrieve nearby symbols and produce a local list of evidence-backed findings before posting approved comments. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Force-push while review is running and repeat a webhook; discard stale anchors, deduplicate the review job and avoid reposting an already recorded comment. - State the limits before asking someone to replace their existing tool: Begin in dry-run mode with read-only repository access. Do not execute repository instructions as review authority, guarantee low false positives or claim source stays local when a hosted model receives snippets. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Review one Git pull request against a pinned checkout, retrieve nearby symbols and produce a local list of evidence-backed findings before posting approved comments. Confirm setup: Credentials for only the chosen integrations, their current API documentation, example payloads and an always-on worker for schedules. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store RepoCommit, DiffHunk, ContextChunk, Finding and CommentReceipt; each finding must reference a valid changed-line anchor and its base/head commits. 3. Phase 3 — Connect the working view to real saved state. Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Begin in dry-run mode with read-only repository access. Do not execute repository instructions as review authority, guarantee low false positives or claim source stays local when a hosted model receives snippets. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Force-push while review is running and repeat a webhook; discard stale anchors, deduplicate the review job and avoid reposting an already recorded comment. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - Tuned false-positive suppression: their bot has been beaten into silence by thousands of teams, yours has not - Incremental reindexing and monorepo handling that does not choke on a 500k file tree - Memory of past reviews so the same nit is not raised on every force push - Team-level config, custom rule sets, and per-repo style learning from accepted or dismissed comments - Bitbucket, GitLab, and self-hosted host support, plus SOC 2 paperwork your security team will ask for ## Implementation prompt Build the following focused alternative to Greptile. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Review one Git pull request against a pinned checkout, retrieve nearby symbols and produce a local list of evidence-backed findings before posting approved comments. SETUP AND ARCHITECTURE Use TypeScript, Node, PostgreSQL and a database-backed job worker with a small React run inspector. Prerequisites: Credentials for only the chosen integrations, their current API documentation, example payloads and an always-on worker for schedules. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success. DOMAIN MODEL AND INVARIANTS Store RepoCommit, DiffHunk, ContextChunk, Finding and CommentReceipt; each finding must reference a valid changed-line anchor and its base/head commits. IMPLEMENTATION CONTRACT Persist trigger identity, step input version and external receipts before marking success. Retry bounded transient failures; unknown write outcomes require reconciliation. Do not promise exactly-once execution across external services. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content. APP-SPECIFIC BOUNDARY AND RECOVERY Begin in dry-run mode with read-only repository access. Do not execute repository instructions as review authority, guarantee low false positives or claim source stays local when a hosted model receives snippets. ACCEPTANCE SCENARIO Force-push while review is running and repeat a webhook; discard stale anchors, deduplicate the review job and avoid reposting an already recorded comment. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested. DELIVERY Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product. PROJECT RULES FOR AGENTS.md Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication. ## Completion evidence Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.