{"uid":"cap_rT6rnVCkY1gayYgmnkLkR","slug":"instructlint-agent-instruction-drift-audit-7f324641","name":"InstructLint Agent Instruction Drift Audit","description":"Audit repository AI instructions against implementation reality, preview public GitHub drift for free, and unlock evidence plus suggested patches for $1 USDC.","url":"https://instructlint.vercel.app/api/report","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"repoUrl":{"type":"string","description":"Canonical public GitHub repository URL."}}},"responseSchema":{"type":"json","example":{"ok":true,"audit":{"mode":"full","score":82,"findings":[{"title":"Documented script does not exist","severity":"high"}]},"repository":{"name":"repository","owner":"owner"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"1","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_NeF7NOFObquGbqsuj24oN","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Audits a public GitHub repository's AI instructions against its implementation reality, returning a drift score, findings, and suggested patches for $1 USDC.","exampleAgentPrompt":"Run an instruction drift audit on https://github.com/myorg/myproject — I want to see the full report with findings and severity scores to check if our AI instructions still match the actual codebase.","exampleUseCases":[{"title":"Pre-release AI config sanity check","prompt":"Before we ship v2, can you audit https://github.com/acmecorp/backend-api for AI instruction drift? I need to know if any documented scripts or behaviors are missing from the actual code."},{"title":"Open source repo quality review","prompt":"I'm evaluating https://github.com/some-user/cool-agent-project for contributions — can you run an InstructLint audit on it and tell me the drift score and any high-severity findings?"},{"title":"Continuous agent instruction monitoring","prompt":"Check https://github.com/myteam/ai-assistant for instruction drift and flag anything where the AGENTS.md or system prompt references something that doesn't exist in the repo anymore."}],"resultDescription":"Returns a JSON object with an 'ok' boolean, an 'audit' object containing the mode ('full' or 'preview'), a numeric drift score (0–100), and an array of findings each with a title and severity level (e.g. high/medium/low), plus a 'repository' object with the owner and repo name.","failureModes":["Invalid or private GitHub repository URL returns an error — only public repos are supported","Malformed URL schema field causes request rejection","Payment of $1 USDC not fulfilled triggers a 402 response before audit is run","Repository with no AI instruction files may return an empty findings array with low informational value","Rate limiting or GitHub API quota issues may cause transient failures"],"whenToPreferThis":"Choose this endpoint when you need to programmatically verify that a public GitHub repository's AI instructions (e.g. AGENTS.md, Copilot instructions, Cursor rules, system prompts) are consistent with its actual implementation. It is especially valuable in CI/CD pipelines, pre-release checks, or agent governance workflows where instruction drift could cause misbehavior. Prefer this over manual review when you need a structured score and actionable findings at scale.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T18:37:28.829Z","isFirstParty":false}