Skip to main content
World Wide TechnologyBenchAI tool benchmarks
Workflow Tool
StatusWatch
SignalDetected
EvidenceGrade B

GSD-Core

43
D 0 vs last quarter

The canonical community continuation of GSD after the May 2026 founder rug-pull — GitHub open-gsd/gsd-core, npm @opengsd/gsd-core (the earlier 'get-shit-done-redux' name is the SAME repo/package, renamed ~2026-05-30, not a competing fork).

UX / DXCapabilityReliabilityValueCommunityEnterpriseAutonomyIntegration

Dimension breakdown

Score · confidence
UX / DX
50% conf50
Capability
50% conf55
ReliabilityIncomplete data at this time
Value
50% conf40
CommunityIncomplete data at this time
Enterprise / Compliance
50% conf25
Autonomy
50% conf55
Integration
50% conf35
Sources blend review platforms, community sentiment, the Signal Radar and practitioner ratings. Scores re-blend each quarter.

The canonical community continuation of GSD after the May 2026 founder rug-pull — GitHub open-gsd/gsd-core, npm @opengsd/gsd-core (the earlier 'get-shit-done-redux' name is the SAME repo/package, renamed ~2026-05-30, not a competing fork). Preserves the well-regarded meta-workflow design (per-phase orchestrators, fresh 200K-token subagent contexts, spec-driven development over 9-15 AI coding runtimes) with all original commits/branches/tags migrated.

Genuinely alive: 5,761 stars, ~25 releases in 5 weeks (v1.6.1 2026-07-01), 100-276 commits/week, and npm downloads now EXCEEDING the abandoned original (9,894 vs 5,951 weekly). For solo devs and small teams wanting a structured scaffold over their AI coding runtime.

Caution

security systemic issues remain OPEN — runtime agent hooks are still advisory-only (warn-but-never-block; independently corroborated by the RokketSec review), the rug-puller still holds npm publish keys to the live original packages (get-shit-done-cc installable; @gsd-build/sdk not even deprecated), and there is no enterprise governance whatsoever.

Critical

unfunded volunteer effort with single-maintainer concentration (trek-e), no governance charter, and a 6-week track record atop a fraud-collapsed provenance.

Recommended

Use cases

Not yet assessed — this section fills in as ACES research covers the tool.

Score caps

Risk flags

  • No codebase indexing

    capabilityConditional

    No codebase indexing or semantic search capability

    Caps Capability at 55

    Removed whenCodebase indexing or RAG capability launched

  • Funding concerns

    stabilityTemporary

    Funding or runway concerns

    Caps Enterprise / Compliance at 50

    Removed whenSuccessful funding round or sustainable business model demonstrated

Assessment

Status rationale

Detected. Initial desk evaluation of a 6-week-old fork.

The traction evidence is strong and Tier-1 (GitHub/npm APIs: 5,761 stars, 100-276 commits/week, npm download leadership over the abandoned original) and the technical design is inherited from a framework historically cited among the three leading Claude Code frameworks. Held at Detected because: (1) no hands-on validation; (2) the two systemic security risks flagged in the independent RokketSec review remain open (advisory-only runtime hooks; npm ownership gap under the rug-puller's control); (3) governance is informal — one dominant maintainer, no charter, no commercial or foundation backstop; and (4) six weeks of post-fork history is too short to establish durability against a provenance of founder exit fraud.

The fork is the trust-bearing successor, but trust is being rebuilt, not yet rebuilt.

Watch for

Movement triggers

Upgrade to Tracked if: (1) runtime enforcement hardens — the four advisory-only agent hooks (prompt-injection / out-of-scope-write) become blocking circuit breakers, confirmed in source, not just release-note language (the v1.6.0 'capability trust gates' govern third-party capability LOADING, not core executor shell access); AND (2) the npm ownership gap closes — original get-shit-done-cc / @gsd-build/sdk packages transferred, frozen, or removed by the registry so the rug-puller no longer holds publish rights; AND (3) governance formalizes beyond one dominant maintainer (GOVERNANCE.md/MAINTAINERS.md, sustained multi-maintainer commit distribution). Upgrade to Assessed additionally requires internal hands-on evaluation.

Downgrade / archive if: release cadence stalls 90+ days (stalled-development), a supply-chain incident exploits the live abandoned packages, trek-e departs without succession (bus factor 1), or the community fragments across incompatible forks (currently minor: jnuyens/gsd-plugin at 71 stars is no threat).

Caution

Risks & limitations

  • No Codebase Indexing

    Moderate

    Radar cap: no-codebase-indexing

  • Funding Concerns

    Moderate

    Radar cap: funding-concerns

Capabilities

Integration surface

Not yet assessed — this section fills in as ACES research covers the tool.

Proof points

Adoption & benchmarks

Not yet assessed — this section fills in as ACES research covers the tool.

Spotted something wrong or missing here? Suggest a change →

Per-source contributions

Click any dimension to see the underlying sources and citations.