@tangle-network/starter-foundry 0.7.3 → 0.13.2

package/registry/families/multi-agent-startup-team-ts/files/roles/hr/methodology/recruiting-loop-design.md

@@ -0,0 +1,222 @@
+---
+capability: recruiting-loop-design
+status: active
+source: hand-authored, drawn from structured-interview research + Amazon bar-raiser pattern
+retrieved: 2026-04-26
+---
+
+# Recruiting Loop Design (HR-led, hiring-manager-defined)
+
+A loop spec produces a `:::artifact` block tagged
+`template: recruiting-loop-design` containing the ordered stages,
+the signal each stage owns, the rubric per stage, the calibration
+plan, and the debrief structure. The loop is calibrated to the
+**level** of the role — a senior loop and a junior loop look
+nothing alike.
+
+## When to run
+
+- Opening a new requisition.
+- Re-opening a role that was closed without a hire — re-calibrate;
+  do not re-run the same loop that produced no signal.
+- A role's panel composition changed by ≥ 50% — re-calibrate
+  before the next candidate.
+- The hiring manager says "the loop isn't telling us anything" —
+  audit and re-design.
+
+## Multi-role contributions
+
+| Slot | Contributor |
+|---|---|
+| Bona-fide qualifications, level expectations, signal weights | Hiring manager (CTO for eng, CMO for growth, CEO for exec) |
+| Loop structure, rubric design, calibration plan, debrief format | HR (you) |
+| Comp band (published in JD per pay-transparency law) | HR + CFO Advisor (band-vs-budget) |
+| Final hire / no-hire decision | Hiring manager + bar raiser |
+
+**Always handoff to the hiring manager peer first** to gather
+bona-fide signals before designing the loop. If CTO has not
+defined the engineering signals at the level, the loop has nothing
+to calibrate against.
+
+## Leveling rubric (loop calibrated to level)
+
+Before composing the loop, agree on the level. The level
+determines which signals matter and at what depth.
+
+- **IC2 / Junior** — executes well-scoped work with guidance.
+  Signal weights: coding mechanics, learning velocity, debugging
+  basics. Lower weight on systems, lower on scope/judgment.
+- **IC3 / Mid** — owns features end-to-end with light direction.
+  Signal weights: coding, debugging, systems-at-feature-scope,
+  collaboration. Mild weight on scope/judgment.
+- **IC4 / Senior** — owns systems, mentors, drives scope across
+  features. Signal weights: systems design, scope/judgment,
+  collaboration, mentorship. Coding mechanics still required, but
+  load-bearing signal shifts upward.
+- **IC5 / Staff** — owns cross-team initiatives, sets technical
+  direction. Heavy weight on systems, scope, influence,
+  cross-functional judgment.
+- **IC6 / Senior Staff and up** — owns org-level technical
+  strategy. Loop becomes more about scope, judgment, vision, and
+  partnership with leadership.
+
+The loop's signal weights MUST match the level. A senior loop
+that spends 80% of time on coding mechanics is mis-calibrated and
+will either over-hire juniors or under-hire seniors who refuse to
+solve a leetcode puzzle.
+
+## Standard loop composition (IC3 / IC4 backend or full-stack)
+
+1. **Recruiter phone screen (30 min)** — work-auth, comp
+   expectation alignment, motivation, level confirmation. The
+   recruiter does NOT score technical signal here.
+2. **Hiring-manager screen (45 min)** — scope, motivation, recent
+   work narrative, level confirmation. Owns the "is this the right
+   level for the role" decision.
+3. **Coding interview (60 min)** — practical coding against a
+   problem the candidate could plausibly hit on the job. NOT
+   leetcode-hard puzzles unless the role actually demands them.
+   Pair-style; candidate writes code; interviewer probes design
+   choices. Owns: coding mechanics + debugging.
+4. **Systems / design interview (60 min)** — design a system at
+   the level's scope. IC3: a feature. IC4: a service. IC5: a
+   cross-service architecture. Owns: systems judgment +
+   trade-off articulation.
+5. **Behavioral / scope interview (45 min)** — STAR-format probes
+   into past work. Owns: collaboration, scope/judgment,
+   mentorship (level-dependent).
+6. **Bar-raiser (45 min)** — outside-team interviewer auditing
+   process integrity, plus one signal not yet covered (often
+   communication or first-principles reasoning). Has veto.
+
+Adjust by role family. A platform-engineering loop swaps
+"coding" for "operational scenario." A growth/marketing loop
+swaps coding for a portfolio-walkthrough + an analytical
+exercise. A staff+ loop adds a cross-functional partnership
+stage.
+
+## Loop adjustments by role family
+
+- **Backend / full-stack engineering** (CTO-defined signals):
+  standard loop above.
+- **Platform / SRE / DevOps** (CTO-defined): swap coding for an
+  operational scenario; add an incident-walkthrough stage.
+- **Growth / marketing leader** (CMO-defined): swap coding for
+  a portfolio-walkthrough; add a positioning-critique stage; add
+  an experiment-design exercise.
+- **Sales / SDR** (CMO-defined): swap coding for a discovery-call
+  role-play; add a deal-walkthrough stage.
+- **Finance / ops** (CFO-defined): swap coding for a model-build
+  exercise; add a board-presentation stage.
+
+## Interview kit per role
+
+The "kit" is the artifact pack the panel uses, version-controlled
+in the ATS or a shared doc:
+
+- **JD** (canonical version, not the public-facing variant if they
+  differ).
+- **Leveling rubric** — the level expectations and signal
+  weights, signed off by the hiring manager.
+- **Per-stage rubric** — see `interview-rubric.md`. One per stage.
+- **Question bank** — anchor + probes per signal, per stage.
+  ≥ 2 problems per stage so the same panelist doesn't run the same
+  problem repeatedly (problem leaks; rotation protects integrity).
+- **Calibration log** — the panel's calibration-session results
+  before the loop opened. Re-calibrate every 3 months or after any
+  panel-composition change.
+- **Reference debrief template** — pre-fillable structure so
+  panelists submit independent reads in the same shape.
+
+The kit lives once per role family. Don't fork per requisition;
+fork per role family and add team-specific notes as a delta layer.
+
+## Debrief structure
+
+The debrief is where bias most often re-enters a structured loop.
+Defend it:
+
+1. **Independent reads first.** Every panelist submits their
+   scored rubric + recommendation BEFORE the debrief meeting. No
+   comments on a shared doc until everyone has submitted.
+   Anchoring is the largest single source of debrief noise; this
+   is the cheapest fix.
+2. **Recommendations are SH / H / LH / NH** (Strong Hire / Hire /
+   Lean Hire (or "Lean No"; org choice) / No Hire). Avoid 3-point
+   scales — the middle absorbs ambiguity.
+3. **Read order in debrief**: scores first (round-robin), then
+   evidence (round-robin), then discussion. Don't let one
+   panelist monologue first.
+4. **Rubric-anchored discussion only.** "I have a feeling about
+   this one" is not admissible without rubric-anchored evidence.
+5. **Bar raiser closes.** They speak last and audit whether the
+   rubric was followed. They have veto.
+6. **Decision logged with reasoning.** The decision and its
+   rubric-anchored rationale go into the ATS so future panels
+   can calibrate against past decisions.
+7. **Hiring manager makes the call** — not HR, not the panel by
+   vote. The hiring manager (CTO for eng, CMO for growth, CEO
+   for exec) carries the rubric-anchored discussion and decides.
+   HR audits the process.
+
+## Output shape
+
+```
+:::artifact
+template: recruiting-loop-design
+date: <YYYY-MM-DD>
+contributors: [hr, <hiring-manager-role>, cfo-advisor?]
+role: <title + level>
+hiring-manager: <ceo | cto | cmo>
+bona-fide-signals: <list, source-tagged to hiring manager>
+level-signal-weights: <map signal → weight per level>
+loop-stages:
+  - { id, owner, duration, signal, rubric-ref, problem-bank-ref }
+calibration-plan:
+  reference-candidate: <transcript or recorded loop ref>
+  pre-launch-session: <date>
+  re-calibrate-cadence: every 3 months | on panel change
+debrief-structure: <independent-reads-first reference>
+comp-band:
+  source: <leveling-doc-link>
+  range-base: <usd>
+  publish-in-jd: true | false (with jurisdiction-justification)
+:::
+```
+
+## Anti-patterns to refuse
+
+- **"Sleep on it" decisions.** If the panel can't anchor a
+  decision in the rubric same-day, the loop didn't gather enough
+  signal. Schedule one more targeted stage rather than letting
+  recency and rumination dominate.
+- **Slack debriefs.** Async debriefs amplify whoever posts first.
+  If async is unavoidable, enforce locked independent reads
+  before any comment thread opens.
+- **Replaying a candidate** with the same panel after a No. If a
+  candidate is reconsidered, run a fresh loop with a fresh panel.
+- **Off-loop signal**: someone "happens to know" the candidate.
+  Move them off the loop or log the relationship as a
+  conflict-of-interest disclosure.
+- **Hiring-manager-by-default-bar-raiser.** The hiring manager
+  has incentive asymmetry; they want to fill the role. Bar
+  raiser is from outside the immediate team.
+
+## Self-check before emitting the loop spec
+
+- Level confirmed; signal weights match. ✅ / ❌
+- Each stage owns a distinct signal; no double-counting. ✅ / ❌
+- Bar raiser is from outside the immediate team. ✅ / ❌
+- Independent-read-before-debrief enforced in the kit. ✅ / ❌
+- Calibration session scheduled before first candidate. ✅ / ❌
+- 4-point recommendation scale (SH/H/LH/NH). ✅ / ❌
+- Comp band sourced + jurisdiction-publication checked. ✅ / ❌
+
+## Source
+
+Frank Schmidt & John Hunter (1998), "The Validity and Utility of
+Selection Methods" — structured interviews ~2x predictive of
+unstructured. Amazon bar-raiser pattern (process-integrity audit,
+veto authority). Lou Adler (performance-based hiring,
+bona-fide-qualifications discipline). Multi-role hiring-manager
+handoff adapted for the startup-team runtime.

package/registry/families/multi-agent-startup-team-ts/manifest.json

@@ -0,0 +1,299 @@
+{
+  "id": "multi-agent-startup-team-ts",
+  "description": "Curated multi-agent startup leadership team \u2014 CEO / CTO / CMO / HR / CFO-advisor with hand-tuned coordination protocols, explicit handoff blocks, and a default-respondent routing rule. Single deploy, five roles, baked-in cadence: weekly review (CEO), 1:1 + tech-debt triage (CTO), positioning + channel experiments (CMO), recruiting loop + interview rubric (HR), burn / runway / fundraise prep (CFO). Each role's system prompt explicitly references the others and routes via :::handoff blocks rather than improvising.",
+  "tags": [
+    "multi-agent",
+    "team",
+    "startup",
+    "advisory",
+    "exec-pod",
+    "leadership-team-agent",
+    "cloudflare-worker"
+  ],
+  "taxonomy": {
+    "language": "markdown",
+    "runtime": "multi-agent",
+    "surface": "multi-agent-team"
+  },
+  "includes": [
+    "agent-base:tangle",
+    "agent-base:secure",
+    "agent-output:blocks",
+    "agent-base:memory",
+    "agent-base:scheduler",
+    "agent-base:mcp-registry",
+    "agent-channels:telegram",
+    "agent-channels:discord",
+    "agent-channels:slack",
+    "agent-channels:whatsapp",
+    "agent-channels:imessage",
+    "agent-channels:gmail",
+    "agent-channels:linear"
+  ],
+  "defaults": {
+    "projectType": "multi-agent-startup-team",
+    "agentName": "startup-team",
+    "publicVars": [
+      "AGENT_NAME"
+    ],
+    "routes": [
+      {
+        "path": "/api/chat",
+        "auth": "bearer",
+        "callsTools": []
+      },
+      {
+        "path": "/api/health",
+        "auth": "none",
+        "callsTools": []
+      }
+    ],
+    "declaredCapabilities": [
+      "team-coordination-protocol",
+      "weekly-review",
+      "decision-journal",
+      "okr-design",
+      "one-on-one-cadence",
+      "tech-debt-triage",
+      "architecture-decision",
+      "positioning-canvas",
+      "channel-experiment-design",
+      "recruiting-loop-design",
+      "interview-rubric",
+      "burn-runway-model",
+      "fundraise-prep"
+    ],
+    "runtime": {
+      "sandbox": "tangle",
+      "noNewPrivileges": true,
+      "capDrop": "ALL"
+    },
+    "stakes": "moderate",
+    "advisoryOnly": true,
+    "schedule": [
+      {
+        "id": "scheduled-1",
+        "cron": "0 14 * * 1",
+        "capability": "weekly-review"
+      },
+      {
+        "id": "scheduled-2",
+        "cron": "0 15 * * 5",
+        "capability": "burn-runway-model"
+      }
+    ],
+    "outboundDomains": [
+      "api.tangle.tools"
+    ],
+    "secrets": [
+      "TANGLE_API_KEY"
+    ],
+    "team": {
+      "defaultRespondent": "ceo",
+      "roles": [
+        "ceo",
+        "cto",
+        "cmo",
+        "hr",
+        "cfo-advisor"
+      ],
+      "agentsConfigPath": "agents.json",
+      "orchestratorPromptPath": "AGENTS.md"
+    }
+  },
+  "files": [
+    {
+      "source": "files/agent.json",
+      "target": "agent.json"
+    },
+    {
+      "source": "files/AGENTS.md",
+      "target": "AGENTS.md"
+    },
+    {
+      "source": "files/agents.json",
+      "target": "agents.json"
+    },
+    {
+      "source": "files/README.md",
+      "target": "README.md"
+    },
+    {
+      "source": "files/roles/ceo/AGENTS.md",
+      "target": "roles/ceo/AGENTS.md"
+    },
+    {
+      "source": "files/roles/ceo/methodology/weekly-review.md",
+      "target": "roles/ceo/methodology/weekly-review.md"
+    },
+    {
+      "source": "files/roles/ceo/methodology/decision-journal.md",
+      "target": "roles/ceo/methodology/decision-journal.md"
+    },
+    {
+      "source": "files/roles/ceo/methodology/okr-design.md",
+      "target": "roles/ceo/methodology/okr-design.md"
+    },
+    {
+      "source": "files/roles/cto/AGENTS.md",
+      "target": "roles/cto/AGENTS.md"
+    },
+    {
+      "source": "files/roles/cto/methodology/one-on-one-cadence.md",
+      "target": "roles/cto/methodology/one-on-one-cadence.md"
+    },
+    {
+      "source": "files/roles/cto/methodology/tech-debt-triage.md",
+      "target": "roles/cto/methodology/tech-debt-triage.md"
+    },
+    {
+      "source": "files/roles/cto/methodology/architecture-decision.md",
+      "target": "roles/cto/methodology/architecture-decision.md"
+    },
+    {
+      "source": "files/roles/cmo/AGENTS.md",
+      "target": "roles/cmo/AGENTS.md"
+    },
+    {
+      "source": "files/roles/cmo/methodology/positioning-canvas.md",
+      "target": "roles/cmo/methodology/positioning-canvas.md"
+    },
+    {
+      "source": "files/roles/cmo/methodology/channel-experiment-design.md",
+      "target": "roles/cmo/methodology/channel-experiment-design.md"
+    },
+    {
+      "source": "files/roles/hr/AGENTS.md",
+      "target": "roles/hr/AGENTS.md"
+    },
+    {
+      "source": "files/roles/hr/methodology/recruiting-loop-design.md",
+      "target": "roles/hr/methodology/recruiting-loop-design.md"
+    },
+    {
+      "source": "files/roles/hr/methodology/interview-rubric.md",
+      "target": "roles/hr/methodology/interview-rubric.md"
+    },
+    {
+      "source": "files/roles/cfo-advisor/AGENTS.md",
+      "target": "roles/cfo-advisor/AGENTS.md"
+    },
+    {
+      "source": "files/roles/cfo-advisor/methodology/burn-runway-model.md",
+      "target": "roles/cfo-advisor/methodology/burn-runway-model.md"
+    },
+    {
+      "source": "files/roles/cfo-advisor/methodology/fundraise-prep.md",
+      "target": "roles/cfo-advisor/methodology/fundraise-prep.md"
+    }
+  ],
+  "validationChecks": [
+    {
+      "type": "file-exists",
+      "path": "AGENTS.md"
+    },
+    {
+      "type": "file-exists",
+      "path": "agents.json"
+    },
+    {
+      "type": "file-exists",
+      "path": "roles/ceo/AGENTS.md"
+    },
+    {
+      "type": "file-exists",
+      "path": "roles/cto/AGENTS.md"
+    },
+    {
+      "type": "file-exists",
+      "path": "roles/cmo/AGENTS.md"
+    },
+    {
+      "type": "file-exists",
+      "path": "roles/hr/AGENTS.md"
+    },
+    {
+      "type": "file-exists",
+      "path": "roles/cfo-advisor/AGENTS.md"
+    },
+    {
+      "type": "agents-md-valid",
+      "path": "roles/ceo/AGENTS.md"
+    },
+    {
+      "type": "agents-md-valid",
+      "path": "roles/cto/AGENTS.md"
+    },
+    {
+      "type": "agents-md-valid",
+      "path": "roles/cmo/AGENTS.md"
+    },
+    {
+      "type": "agents-md-valid",
+      "path": "roles/hr/AGENTS.md"
+    },
+    {
+      "type": "agents-md-valid",
+      "path": "roles/cfo-advisor/AGENTS.md"
+    },
+    {
+      "type": "schedule-valid",
+      "path": "manifest.json"
+    }
+  ],
+  "contextHints": {
+    "commands": [],
+    "entrypoints": [
+      "AGENTS.md",
+      "agents.json"
+    ],
+    "extensionPoints": [
+      "roles/",
+      "AGENTS.md"
+    ]
+  },
+  "keywords": [
+    "startup-team",
+    "executive-team",
+    "leadership-team",
+    "founders-team",
+    "exec-pod",
+    "multi-agent-team",
+    "advisory-pod",
+    "team-cadence"
+  ],
+  "tieredKeywords": {
+    "tier1": [
+      "startup-team-agent",
+      "startup team agent",
+      "executive-team-agent",
+      "executive team agent",
+      "leadership-team-agent",
+      "leadership team agent",
+      "founders-team-agent",
+      "founders team agent",
+      "exec-pod",
+      "exec pod",
+      "advisory-pod"
+    ],
+    "tier2": [
+      "team-cadence",
+      "team cadence",
+      "multi-role-team",
+      "co-founder-pod",
+      "ceo-cto-cmo",
+      "burn-runway",
+      "okr-design",
+      "decision-journal",
+      "weekly-review",
+      "recruiting-loop"
+    ],
+    "tier3": [
+      "agent"
+    ],
+    "archetypes": [
+      "multi-agent-team",
+      "advisory-pod"
+    ]
+  }
+}

package/registry/families/multimodal-agent/files/api/README.md

@@ -42,7 +42,7 @@ const app = express()
 const upload = multer({ storage: multer.memoryStorage(), limits: { fileSize: 20 * 1024 * 1024 } })
 const client = new Anthropic({
   baseURL: 'https://router.tangle.tools/anthropic',
-  apiKey: process.env.TANGLE_ROUTER_USER_KEY,
+  apiKey: process.env.TANGLE_API_KEY,
 })
 
 app.post('/api/multimodal', upload.fields([{ name: 'image' }, { name: 'audio' }]), async (req, res) => {

package/registry/families/multimodal-agent/files/package.json

@@ -26,6 +26,8 @@
   "pnpm": {
     "overrides": {
       "vite": "^6.4.2"
-    }
+    },
+    "minimumReleaseAge": 4320,
+    "minimumReleaseAgeExclude": []
   }
 }

package/registry/families/nextjs-ts/files/package.json

@@ -35,6 +35,8 @@
   "pnpm": {
     "overrides": {
       "vite": "^6.4.2"
-    }
+    },
+    "minimumReleaseAge": 4320,
+    "minimumReleaseAgeExclude": []
   }
 }

package/registry/families/observable-notebook/files/package.json

@@ -21,6 +21,8 @@
   "pnpm": {
     "overrides": {
       "vite": "^6.4.2"
-    }
+    },
+    "minimumReleaseAge": 4320,
+    "minimumReleaseAgeExclude": []
   }
 }

package/registry/families/observable-notebook/manifest.json

@@ -104,7 +104,24 @@
     "tier2": [
       "observable",
       "reactive dashboard",
-      "data loader"
+      "data loader",
+      "algorithm",
+      "data structure",
+      "suffix array",
+      "sais",
+      "graph traversal",
+      "dynamic programming",
+      "competitive programming",
+      "algorithm visualizer",
+      "research notebook",
+      "computational notebook",
+      "scientific notebook"
+    ],
+    "archetypes": [
+      "algorithm visualization",
+      "data-structure walkthrough",
+      "research dashboard",
+      "interactive paper"
     ]
   }
 }

package/registry/families/ollama-server/files/package.json

@@ -10,5 +10,9 @@
   "devDependencies": {
     "tsx": "^4.19.2",
     "typescript": "^5.9.0"
+  },
+  "pnpm": {
+    "minimumReleaseAge": 4320,
+    "minimumReleaseAgeExclude": []
   }
 }