pod
Other formats agents might prefer:
markdownjsonllms.txt

Agent? You probably want markdown or json, or Pod over MCP.

Reported issues for tierward

Pod holds 7 of 7 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to tierward.

Most discussed

Q3 #4b — MCP-aware audit skills (ICE 210)

Pull live data into selected audit skills instead of bundling static patterns at release time. Initial scope: /security-audit, /arch-audit, and one more audit skill (likely /dependency-audit or /infra-audit).

What changes per skill

  • /security-audit reads the CVE database from a vetted CVE MCP server. It catches CVEs published hours ago, not the snapshot frozen at the last CDK release.
  • /arch-audit reads the Anthropic spec from an MCP-published source when one exists. Deprecati

Read the thread · 2026-04-26 · open · outside contributor · 2 comments

Anthropic spec compliance: allowed-tools syntax + progressive disclosure

Problem

Two spec deviations documented in docs/reviews/anthropic-spec-deviations.md:

  1. allowed-tools comma-separated syntax (§2.4): all 39 SKILL.md files use Read, Glob, Grep but Anthropic spec requires space-separated or YAML list. If the parser treats commas as literal characters, tool pre-authorization is silently broken across every scaffolded project.

  2. File size >500 lines (§2.5): arch-audit (549 lines × 3 tiers) and perf-audit (528 lines × 3 tiers) exceed the Anthrop

Read the thread · 2026-04-17 · closed · 1 comment

New skill: /migration-audit

DB migration validation, data loss prevention, rollback checks. Stack-aware.

Ref: roadmap-v1.9.1.md skill expansion rank #2

Read the thread · 2026-04-11 · closed · 1 comment

Public documentation site (VitePress)

Getting Started + Contributing a Skill + Architecture overview. README alone does not scale for community growth.

Ref: roadmap-v1.9.1.md Q1 deliverable #4

ICE Score: 432 (I:9 C:8 E:6)

Read the thread · 2026-04-11 · closed · 1 comment

Q3 #4d — /pr-review skill (autonomous local PR review, ICE 267)

The /pr-review skill ports a staff-manager PR-review flow into CDK as a local, auditable alternative to external GitHub review apps. It resolves a PR number from the argument or the current branch, pulls the diff with gh pr diff, runs a review agent against it, posts the result as a PR comment, and prompts the user for a merge decision.

Why ship it now. The 2026-04-26 cross-LLM evaluation returned four unanimous SHIP votes from GPT-4.1, Gemini 2.5 Pro, Mistral Large, and Perplexity Sonar Pr

Read the thread · 2026-04-26 · closed · 0 comments

Q3 #4a — CDK governance MCP server (ICE 294)

A local MCP server that exposes CDK's existing JSON outputs as MCP tools. Any MCP-aware client (Claude Desktop, ChatGPT desktop, Cursor, VS Code, Copilot Studio) can query CDK project health without the CDK CLI installed.

Tool surface, initial scope:

  • cdk_doctor_report — returns the doctor --report JSON
  • cdk_team_settings — returns the parsed .claude/team-settings.json, or null when absent
  • cdk_arch_audit_status — returns last arch-audit run timestamp and summary
  • `cdk_skill_inven

Read the thread · 2026-04-26 · closed · outside contributor · 0 comments

GitHub MCP for pipeline merge/push

Replace shell git merge && git push in Phase 5c/8 with GitHub MCP. Reduces shell dependency for Git workflow.

Ref: roadmap-v1.9.1.md Q2 deliverable #7

Read the thread · 2026-04-11 · open · 0 comments

Most recent

The remaining reports are on the project's issue tracker.