Skip to content

v15.16.0

Latest
Latest

Choose a tag to compare

View all tags
@sickn33 sickn33 released this 20 Aug 07:00
v15.16.0
b6ceca3
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

[15.16.0] - 2026-08-20 - "Agent Reliability, Evidence Integrity, and Stack Audits"

Added six focused skills for asynchronous C++ networking, controlled agent
fault injection, run-evidence auditing, orchestration review, measurable UI
quality, and multi-source research, while adding cross-artifact stack checks
and modernizing YouTube transcript extraction. The published catalog contains
2,025 skills.

This release helps Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and
related AI coding assistants test agent harnesses safely, distinguish run claims
from inspectable evidence, review multi-agent control flow, score recurring UI
failure modes, and keep research conclusions honest when sources disagree.

Start here:

Added

  • Added boost-asio-pro for production-oriented
    asynchronous C++ networking with Boost.Asio, including composed operations,
    cancellation, coroutine lifetimes, strands, backpressure, and testable error
    paths (#1186).
  • Added
    agent-harness-fault-injection for
    controlled timeouts, malformed outputs, partial failures, and recovery checks
    with explicit blast-radius, consent, rollback, and evidence requirements
    (#1189).
  • Added audit-agent-run-evidence for
    read-only auditing of agent-run claims against recorded events, artifacts,
    timestamps, identifiers, and reproducible verification steps
    (#1192).
  • Added
    review-multi-agent-orchestration
    for reviewing delegation boundaries, shared-state hazards, handoff contracts,
    retry behavior, convergence, and evidence quality in multi-agent systems
    (#1193).
  • Added ui-slop-score for scoring recurring generic
    interface patterns against a concrete product brief, reference evidence,
    accessibility constraints, and a transparent weighted rubric
    (#1196).
  • Added multi-source-search for bounded research
    across optional providers with claim-level citations, source polarity,
    conflict tracking, URL canonicalization, and an offline validation script
    (#1202,
    #1205).

Changed

  • Added a read-only aas stack audit flow and paired browser-local Workbench
    comparison for detecting digest, catalog, target, and exact skill-set drift
    between stack artifacts without applying either stack
    (#1199).
  • Updated the YouTube transcript extractor for both legacy 0.6.x and modern 1.x
    youtube-transcript-api interfaces, common YouTube URL forms, and UTF-8 output
    on legacy Windows consoles, with isolated network-free regression tests
    (#1198).
  • Hardened multi-source evidence validation so every source is classified as
    supporting or contradicting, conflicts agree with that classification, and
    superficial URL variants cannot inflate source diversity
    (#1205).
  • Regenerated the canonical catalog, offline AAS Core data, web assets,
    marketplaces, editorial bundles, compatibility reports, and Codex/Claude
    plugin distributions for 2,025 skills.

Security

  • Kept fault injection opt-in, bounded to an approved environment, and gated by
    explicit preconditions, abort thresholds, rollback, recovery verification,
    and evidence capture before any resilience claim is accepted.
  • Kept run-evidence and orchestration review read-only by default: neither skill
    treats missing telemetry as success or authorizes repairs, retries, or
    production actions without a separate user-approved step.
  • Kept multi-source provider access optional and explicit, with credentials out
    of report artifacts and an offline validator that fails closed on missing
    evidence, inconsistent conflict state, or duplicate canonical sources.
  • Kept stack comparison local and non-applying; artifact mismatches are reported
    before any installation or workspace mutation can be considered.

Who should care

  • C++ teams building asynchronous network services that need explicit lifetime,
    cancellation, serialization, backpressure, and shutdown contracts.
  • Agent-platform teams testing failure recovery or auditing whether reported run
    outcomes are actually supported by durable evidence.
  • Multi-agent system owners reviewing delegation, shared-state, retry, and
    convergence risks before expanding autonomy.
  • Product and design teams that want a repeatable anti-generic UI score tied to
    a real brief rather than subjective aesthetic claims.
  • Researchers and maintainers who need conflict-aware multi-source reports and
    exact stack-artifact drift detection.

Validation

  • Passed repository validation, reference validation, documentation-security
    checks, warning-budget enforcement, the complete repository test suite,
    plugin-compatibility and bundle checks, web-app install/build/prerender, and
    the npm package dry run on the protected release base.
  • Reviewed all six added skills and their bundled files for semantics, safety,
    provenance, declared risk, limitations, consent boundaries, and relevant
    regression coverage; also reviewed the YouTube compatibility and stack-audit
    changes against their isolated tests.

Limitations

  • Fault injection can demonstrate behavior only in the tested environment and
    scenario; it does not prove resilience to untested failures or authorize
    experiments against production systems.
  • Evidence audits and orchestration reviews expose unsupported claims and
    control-flow risks but do not reconstruct missing telemetry or implement the
    fixes they recommend.
  • ui-slop-score is a transparent heuristic tied to supplied references and
    constraints, not an objective guarantee of visual quality or user success.
  • Multi-source research still depends on source availability and provider
    access; source count cannot replace source quality, and unresolved conflicts
    remain unresolved in the final report.
  • Stack audit detects artifact drift but intentionally does not choose a winner
    or mutate an installation.

Credits

Assets 2
Loading