AI Agent Workflow Collection

Single source of truth for audit items covering text that an agent executes as instructions. Definitions live in items/ .md; audit skills reference items by slug.

Promote a review finding or bug fix into a contract test that prevents the underlying invariant violation from recurring. Companion to finding-to-audit, which elevates to diff-time rules instead.

Configure and run cargo-mutants for Rust mutation testing — invoking runs, reading mutants.out, writing excludere patterns matching cargo-mutants' mutant-name format, and choosing excludere vs [mutants::skip].

Narrow Codex pass on a newly added contract test, verifying it is not tautological and would fail on the original buggy implementation. Lightweight alternative to the full codex-review / copilot-review loop.

Audit a test suite for structural debt — fixtures that trivialize the code under test, tautological differential assertions, implementation-locked or assertion-less tests, and name-claim mismatches. Optional scope argument (file path, directory, or module name); without arguments, audits the workspace's test surfaces. Companion to driftreaper / breachreaper.

Single source of truth for the diff root — the ref a change is measured from — covering the consumer contract, where the root comes from, and the per-command range conversion. Definition file, not a procedure.

Single-pass audit of the current diff against the applicable quality rule sets before declaring a task complete or requesting external review.

Audit docstrings for drift — claims that no longer match actual code behavior. Optional scope argument (file path, directory, or module name); without arguments, audits the entire workspace.

Draft an Architecture Decision Record (a timeless decision, distinct from an implementation schedule) and write the file. Use file-issue instead when the artifact is a task list, bug report, or phase plan.

Draft README.md or visitor-facing markdown (top-level .md, docs//.md) using the canonical skeleton, complementing the public-doc-durability audit.

Draft and file a GitHub PR using gh-body-conventions and the PR body skeleton, via the gh-post wrapper. Supports a gate mode that stops at user approval.

Promote a review finding into a pre-commit audit rule that catches the diff-inspectable issue class (import direction, pub widening, debug artifacts, dropped FFI output). Companion to bug-to-contract.

Single source of truth for per-finding review-triage dispositions and response selection for actionable findings, which the review and audit skills apply by reference.

Promote a late-caught defect — one an earlier gate should have caught — into a development-skills issue proposing a fix to that gate's procedure.

Audit a drafted or filed GitHub issue / PR body against gh-body-conventions via a fresh-context subagent. Any unresolved ⚠ blocks the caller.

Single source of truth for GitHub issue / PR body conventions — semantic line breaks, LaTeX-safe math, reference / exclusion policies, language defaults. Definition file, not a procedure.

Land a large change too big for one PR as a sequence of PRs merging into a long-lived integration branch, then a final PR into main. Use when one PR would exceed a reviewer's diff-size limit, or when multiple components' APIs must migrate together (cross-component migration, large refactor, multi-PR feature).

Single source of truth for universal code-quality items. Definitions live in items/ .md; audit and preflight skills reference items by slug.

End-to-end wrapper running research-and-implement then review-pipeline on a GitHub issue, carrying it from investigation through the user-controlled merge gate.

Work a GitHub issue end to end in two phases — research, then implement — under quaere-evidence and quaere-execution discipline.

Append a normalized per-run record of reviewer-gate performance (findings, dispositions, duplicates, cost) to the local telemetry log after a review pipeline run finishes.

Rules for implementing a Rust safe wrapper around an external (C / Fortran / FFI) call. Read before writing unsafe FFI blocks, extern "C" declarations, or bindgen-based wrappers.

Audit C++ source for known-bad standard library defaults (std::function, std::regex, std::list, std::map, std::unorderedmap, std::async, std::vector , etc.) using a TSV-driven rule table that is extended by appending lines. Wraps a ripgrep-based shell script; reports per-rule hit counts and sample locations, exits non-zero on configurable severity (for CI). Targets C++17+ codebases.