hima

Bootstrap a new project or catch up an agent on an existing one in minutes by reading vision/goals/state and scaffolding the minimum brain files.

Produce the structural plan — component boundaries, contracts, data flow — plus a lightweight decision record, from a sealed charter.

Formalize intent into a spec artifact (Gherkin scenarios, acceptance criteria, criticality tags) before any non-md file may change.

Declare and audit the per-project disciplines (cadence, branching, testing, architecture, methodology) that the pluggable StageSkillMap resolves against.

Implement the minimum code to satisfy the charter's RED tests, one logical change per commit.

Cited, multi-source research pass for H/C decisions or true blockers — converts findings into requirements, risks, and rejected alternatives.

Bridge blueprint to forge — break an approved charter+blueprint into atomic, sequenced or explicitly-parallel steps, cross-critiqued once before trust.

Batch every open question into ONE numbered list instead of serial one-at-a-time interrogation when no safe reversible default exists.

Structural-only cleanup pass — dead code, simplification, AI-slop rejection — with zero behavior change, always its own S-commit.

Ongoing post-ship guardianship — dependency hygiene, regression watch, dead-code sweep, health scorecard against real code.

Map the problem before any charter exists — topology, dependencies, unknowns, requirement framing.

For bug reports and runtime failures, enforce root-cause-before-fix — reproduce, isolate cause, fix minimally, add a regression test.

Write and run the tests that prove each charter scenario; accumulate the evidence no completion claim may skip.

Independent critic that inspects work against the charter and seals a stage DONE_VERIFIED, PARTIAL, or BLOCKED.

Prove a change works end-to-end by driving the real flow — the dynamic counterpart to hima-verdict's static review.

Define a reachable ICP access path before spending build effort.

Source product seeds without treating discovery signals as PMF proof.

Separate PMF evidence from inference, assumption, and risk before validation claims.

Score problem pain with explicit evidence and hard kill gates.

Sequence PMF validation tests from cheapest signal to strongest proof.

Define the market category thesis and reject misleading frames.

Align sprint work to product goals and keep unrelated work out.

Build a message hierarchy with claims bounded by available proof.

Map product positioning against alternatives with evidence-backed differentiation.

Express strategy as a choice with an explicit rejected alternative.

Audit hidden assumptions and attach verification plans before decisions harden.

Synthesize discovery findings with confidence and next actions.

Map claims to concrete evidence artifacts and expose unsupported gaps.

Triangulate claims across independent sources before relying on them.

Scan a technical surface and map relevant files, boundaries, and risks.

Translate requirements into observable acceptance criteria and coverage gaps.

Shape schema and interface requirements into explicit contract fields and compatibility risks.

Convert ambiguous intent into testable requirement statements with explicit assumptions.

Review a specification for readiness, missing obligations, and testability before build.

Map specification claims to a focused verification plan and identify untested claims.

Check user-facing changes for accessibility barriers and minimal fixes.

Review interaction flows for friction, missing states, and inefficient steps.

Review interface copy for clarity, actionability, and missing states.

Audit layout and visual hierarchy for scanability and priority clarity.

Review repeated-use workflows for operator efficiency and practical UX improvements.