Skip to content

Add 4 starter agent templates (growth, designer, devops, founder) + cascade develop→main#3

Merged
evereq merged 3 commits into
mainfrom
develop
Jul 17, 2026
Merged

Add 4 starter agent templates (growth, designer, devops, founder) + cascade develop→main#3
evereq merged 3 commits into
mainfrom
develop

Conversation

@evereq

@evereq evereq commented Jul 17, 2026

Copy link
Copy Markdown
Contributor

Cascades develop into main so the platform (which reads ref main) picks up the four new starter agent templates.

New templates (existing 8 unchanged)

  • starter-growth — Growth / SEO Strategist (TENANT)
  • starter-designer — Designer (UI/UX) (WORK)
  • starter-devops — DevOps / SRE (WORK)
  • starter-founder — Founder / Product Strategist (MISSION)

Each adapts an MIT-licensed public subagent (VoltAgent/awesome-claude-code-subagents, wshobson/agents) into this repo's SOUL.md + .works/agent.yml format, with skills.yml, kb/, prompts/, and an eval/<slug>.yml. manifest.json gains 4 index rows; README gains MIT source attribution.

Validated locally against the repo's ajv schemas: 12/12 templates valid.

Also brings the two prior CI commits already on develop (self-hosted ARC runner + Node-24 action bumps) onto main as part of the normal cascade (no cherry-pick).

🤖 Generated with Claude Code

evereq and others added 3 commits July 8, 2026 14:47
* ci: move Linux CI to sized self-hosted ARC (-4/-8) + actionlint

* chore: Convert CI to portable self-hosted/GitHub-hosted pattern - Transform 1: runs-on replaced with org variable fallback
…oves Node-20 deprecation warnings) [skip ci]
Extends the catalog from 8 to 12 templates (existing 8 unchanged).
Each adapts an MIT-licensed public subagent into this repo's
SOUL.md + .works/agent.yml format, with skills.yml, kb/, prompts,
and an eval:

- starter-growth  (Growth / SEO Strategist, TENANT)  <- VoltAgent seo-specialist/growth-loops + wshobson seo-*
- starter-designer (Designer UI/UX, WORK)            <- VoltAgent ui-designer + wshobson ui-ux-designer
- starter-devops  (DevOps / SRE, WORK)               <- VoltAgent devops-engineer/sre-engineer + wshobson devops-troubleshooter
- starter-founder (Founder / Product Strategist, MISSION) <- VoltAgent product-manager/market-researcher

manifest.json gets 4 index rows; README gains MIT source attribution.
Validated against the repo's ajv schemas (12/12 templates valid).

Co-Authored-By: Claude Opus 4.8 <[email protected]>
@ecc-tools

ecc-tools Bot commented Jul 17, 2026

Copy link
Copy Markdown

Analyzing 200 commits...

@evereq
evereq merged commit 74d64da into main Jul 17, 2026
1 check failed
@ecc-tools

ecc-tools Bot commented Jul 17, 2026

Copy link
Copy Markdown

Analysis Complete

Generated ECC bundle from 3 commits | Confidence: 60%

View Pull Request #4

Repository Profile
Attribute Value
Language TypeScript
Framework Not detected
Commit Convention mixed
Test Directory separate
Changed Files (56)
Metric Value
Files changed 56
Additions 2102
Deletions 24

Top hotspots

Path Status +/-
eval/starter-designer.yml added +87 / -0
eval/starter-founder.yml added +85 / -0
eval/starter-growth.yml added +83 / -0
eval/starter-devops.yml added +81 / -0
templates/starter-growth/SOUL.md added +73 / -0

Top directories

Directory Files Total changes
eval 4 336
templates/starter-devops 4 142
templates/starter-founder 4 134
templates/starter-designer 4 132
templates/starter-growth 4 132
Analysis Depth Readiness (evidence-backed, 64%)

ECC Tools uses this to decide whether recommendations should stay at commit-history/setup guidance or expand into CI, security, harness, reference-set, AI-routing, and team backlog work.

Area Status Evidence / Next Step
Commit history Partial 3 commits sampled
CI/CD signals Ready .github/workflows/validate.yml
Security evidence Missing Add AgentShield, audit, SARIF, SBOM, or security review evidence so recommendations can cover security posture.
Harness configuration Missing Add Claude, Codex, OpenCode, Zed, dmux, MCP, plugin, or cross-harness config evidence for harness-agnostic recommendations.
Reference/eval evidence Ready eval/starter-designer.yml, eval/starter-devops.yml, eval/starter-founder.yml
AI routing and cost controls Ready templates/starter-designer/prompts/system.md, templates/starter-designer/prompts/tasks/component-spec.md, templates/starter-designer/prompts/tasks/design-review.md
Team handoff and project tracking Ready templates/starter-founder/prompts/tasks/roadmap-prioritization.md
Reference Set Readiness (0/7, 0%)
Area Status Evidence / Next Step
Deep analyzer corpus Missing Add analyzer fixture, golden, benchmark, or reference-set files that can catch analyzer regressions.
RAG/evaluator comparison Missing Add retrieval or evaluator reference-set comparison fixtures with expected ranking behavior.
PR salvage/review corpus Missing Add stale-PR, review-thread, reopen-flow, or salvage reference cases for queue cleanup automation.
Discussion triage corpus Missing Add public discussion triage fixtures, golden cases, or reference sets for informational, answered, and no-response classifications.
Harness compatibility Missing Add cross-harness, adapter-compliance, or harness-audit evidence for Claude, Codex, OpenCode, Zed, dmux, and agent surfaces.
Security evidence Missing Attach security evidence such as SBOMs, SARIF, audit reports, or AgentShield evidence packs.
CI failure-mode evidence Missing Add captured CI failure logs, dry-run fixtures, or troubleshooting docs for common workflow failure modes.
Likely Future Issues (3)
Severity Signal Why it may show up
MEDIUM Cost or token-risk changes may ship without budget evidence 16 cost/token-risk paths changed; 0 budget, usage, or cost validation artifacts changed
MEDIUM CI workflow changes may ship without failure-mode evidence 1 CI/test-runner paths changed; 0 CI failure-mode evidence artifacts changed
MEDIUM Dependency or CI drift could surface after merge CI/workflow files changed; no lockfile changes detected
  • Cost or token-risk changes may ship without budget evidence: The PR changes AI routing, usage, token budget, or model-call surfaces without touching obvious budget, usage-limit, or cost regression evidence.
  • CI workflow changes may ship without failure-mode evidence: The PR changes CI workflows or test-runner entrypoints without touching CI failure fixtures, captured logs, troubleshooting notes, or regression evidence.
  • Dependency or CI drift could surface after merge: Package or workflow changes landed without an accompanying lockfile update, which often turns into CI or release noise later.
Suggested Follow-up Work (3)
Type Suggested title Targets
PR test: add budget evidence for templates/starter-designer/prompts/system.md + templates/starter-designer/prompts/tasks/component-spec.md templates/starter-designer/prompts/system.md, templates/starter-designer/prompts/tasks/component-spec.md
PR ci: add failure-mode evidence for .github/workflows/validate.yml .github/workflows/validate.yml
PR chore: refresh lockfile and validate CI after dependency updates .github/workflows/validate.yml
  • test: add budget evidence for templates/starter-designer/prompts/system.md + templates/starter-designer/prompts/tasks/component-spec.md: Backfill cost, token, or usage-limit validation before another model-routing change lands on the touched surface.
  • ci: add failure-mode evidence for .github/workflows/validate.yml: Backfill CI failure-mode evidence before another workflow or test-runner change lands on the touched surface.
  • chore: refresh lockfile and validate CI after dependency updates: Package or workflow changes without a lockfile refresh tend to turn into noisy follow-up fixes after merge.

Copy-ready bodies

test: add budget evidence for templates/starter-designer/prompts/system.md + templates/starter-designer/prompts/tasks/component-spec.md

## Summary
- Add budget or usage-limit validation for the recently changed AI routing or model-call surface.

## Why
- Backfill cost, token, or usage-limit validation before another model-routing change lands on the touched surface.

## Touched paths
- `templates/starter-designer/prompts/system.md`
- `templates/starter-designer/prompts/tasks/component-spec.md`

## Validation
- Add or extend budget, token, usage-limit, or model-routing regression coverage for the changed path.
- Verify the route still enforces plan limits, retry caps, fallback behavior, or explicit cost controls.

ci: add failure-mode evidence for .github/workflows/validate.yml

## Summary
- Add CI failure-mode evidence for the recently changed workflow or test-runner surface.

## Why
- Backfill CI failure-mode evidence before another workflow or test-runner change lands on the touched surface.

## Touched paths
- `.github/workflows/validate.yml`

## Validation
- Add or update a CI failure fixture, captured failing log, troubleshooting note, workflow dry-run evidence, or regression test for the changed CI/test-runner behavior.
- Run the affected workflow or test-runner entrypoint locally or in CI and record pass/fail evidence.

chore: refresh lockfile and validate CI after dependency updates

## Summary
- Refresh the lockfile and rerun CI after the dependency or workflow changes in this PR.

## Why
- Package or workflow changes without a lockfile refresh tend to turn into noisy follow-up fixes after merge.

## Touched paths
- `.github/workflows/validate.yml`

## Validation
- Refresh the lockfile in the same package manager used by the repo.
- Run the repo typecheck / test / CI entrypoints that depend on the updated package graph.
Generated Instincts (15)
Domain Count
git 3
code-style 9
testing 2
workflow 1

After merging, import with:

/instinct-import .claude/homunculus/instincts/inherited/agents-instincts.yaml

Files

  • .claude/ecc-tools.json
  • .claude/skills/agents/SKILL.md
  • .agents/skills/agents/SKILL.md
  • .agents/skills/agents/agents/openai.yaml
  • .claude/identity.json
  • .codex/config.toml
  • .codex/AGENTS.md
  • .codex/agents/explorer.toml
  • .codex/agents/reviewer.toml
  • .codex/agents/docs-researcher.toml
  • .claude/homunculus/instincts/inherited/agents-instincts.yaml

ECC Tools | Everything Claude Code

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant