Pre-open repo agent-surface audit — by TextForAgents LLC. Before your agent opens that repo, know what in it will run — or reconfigure your agent: a per-harness OPEN / OPEN-QUARANTINED / DO-NOT-OPEN verdict on the repo's complete agent-control surface, with a sanitised copy that re-audits clean. A repository that arrives as files can execute code and rewrite its own review before your agent's first prompt. Its .git/config can name programs — core.fsmonitor, hooksPath, sshCommand, filter and diff drivers — that your harness's own background git status runs as you, outside the sandbox, without an approval prompt. And its own subagent definitions can quietly downgrade the reviewing model, exclude the directory where the payload sits, and instruct the reviewer not to re-audit. This service is the pre-open gate: it never executes the tree; it enumerates the complete agent-control surface on two separately graded surfaces — EXECUTION (git-config command sinks, hooks and hooksPath targets at any depth, .gitattributes drivers, submodule ext:: URLs, MCP server commands, package lifecycle scripts) and EXAMINATION (model pins against your pinned policy, review-scope exclusions including implicit "only review X" omissions, do-not-reaudit clauses, permission widenings, unbounded agent-binding prose) — issues a verdict for your exact harness and version from a maintained patch-status matrix, signs a receipt whose tree hash binds file contents, and can emit a sanitised quarantined copy accepted only when it re-audits with zero high findings.
Stated plainly: a verdict grades the enumerated agent-control surface against your policy and the patch matrix — it is not a general malware or safety determination about a tree's code; enumeration is complete on the covered classes, but prose classification is pattern-based, so a genuinely novel paraphrase can escape classification while never escaping enumeration; the patch matrix is a maintained asset and each verdict records the matrix version it stands on; willingness to pay is unmeasured — nobody sells a pre-open verdict before.
Verdict lookup $0.01/query · Pre-open audit $0.99/tree · Audit + sanitised copy $1.99 · Operator $9.99/mo (50 fresh audits included) · Fleet $19.99/mo (200 fresh audits included) (x402). One free pre-open audit, one time per operator.
API endpoint · OpenAPI spec · Agent guide · Support: support@textforagents.com