app.repopilot/repopilot
name:app.repopilot/repopilot
Repository evidence for agents before they adopt dependencies, enter codebases, compare, or merge.
- transport:
- remote
- credential class:
- self-provisionable
Owner verification
Not yet verified. Verifying proves you control this server and is free, permanently — it never changes a published score.
Start verification →Tools
- analyze_reposhallow
CALL when entering an unfamiliar repository or deciding whether to depend on, fork, learn from, or deploy it. Returns a concise four-use-case brief, watchouts, evidence confidence, architecture summary, freshness, and next actions without dumping the full generated artifact. Use get_artifact when file-level orientation is needed. Pass exactly one of repo or package.
- check_change_riskshallow
CALL before merging a pull request or after producing a local diff. Returns a deterministic 0-10 change-shape score with receipts for size, spread, missing tests, sensitive paths, hotspots, and blast radius. Pass repo+pr OR diff; repo may accompany diff for cached hotspot context. This prioritizes review and never approves a merge.
- check_dependencyshallow
CALL when the user or agent is about to add, upgrade, trust, fork, or deploy an npm package or public GitHub repository. Returns a lean repository-level recommendation, confidence, evidence gaps, CVEs, maintenance, ownership, license, CI/tests, Scorecard, freshness, and next actions. DO NOT use for code navigation. Pass exactly one of repo or package. A favourable result does not validate an exact package version or compatibility.
- compare_reposshallow
CALL when the user is choosing between exactly two dependencies or repositories. Returns the preferred candidate for each use case, material trade-offs, confidence, and evidence gaps. Each target is owner/repo, a GitHub URL, an npm package name, or npm:@scope/pkg. Cached full analyses are preferred; a miss uses bounded live GitHub/OpenSSF evidence with limited confidence and explicit unknowns rather than guessing.
- evaluate_dependency_changeshallow
CALL immediately before adding or upgrading an npm dependency, while you still have the package name and target version in hand. Answers "is this specific version safe to take on" from registry metadata, advisory deltas, provenance, license, and repository evidence, and returns blockers, warnings, a recommendation, and a verification plan. The minimum call is {"change":{"name":"lodash"}} — everything else is optional, including the target version, which defaults to the latest published version exactly as `npm install <pkg>` would. Give the target as an exact version, a dist-tag, or a SemVer range; it resolves to one exact version, reported in change.to_version. Add the optional `project` snapshot to also get Node/peer/license compatibility. Common alias and case-variant field names are repaired rather than rejected, and every repair, default, and resolution is listed in input_adjustments — read it to see what was actually evaluated. Rejections are correctable: they name the field, why it failed, and a working example. Evaluates only; never installs or edits anything.
- get_artifactshallow
CALL before substantial code work in an unfamiliar repository when the agent needs key files, entry points, architecture hypotheses, a reading order, and verify-before-trusting guidance. Returns the cached CLAUDE.md-style artifact or Cursor rules. Do not call again if the artifact is already in context. Pass exactly one of repo or package.
- plan_repo_taskshallow
CALL before editing an unfamiliar public repository. Returns a bounded reading order, relevant files, dependency consumers, test/verification obligations, analyzed-vs-checked SHA relation, evidence provenance, and a short-lived verification contract. Task text is used only for bounded local matching and is never persisted raw.
- verify_dependency_changeshallow
CALL after changing the manifest/lockfile and running local checks. Compares the exact evaluated target with the resolved result and caller-reported proof receipts, reports missing/failed evidence and residual risk, and labels receipts as caller asserted. It never runs commands or stores diff/check output.
Embed this server’s score
Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.
[](https://vouch.tools/servers/8cceb8f1-e369-4eae-8242-7f96d3fe88ae)