denis@keisei — keiseikit-browse — 144×42
⌘1
KEISEIKIT v0.16.2DAEMON UPSLEEP 03:07
session 4f3amem 47/2002026-05-01 05:21

$ ls /agents/ | wc -l → 37

/agents fleet

Sub-agents are spawned via the Agent tool with subagent_type=<name>. Every non-trivial spawn forks its own git branch, writes a 6-file artefact bundle, and registers a row in kei-ledger (RULE 0.12).

tiers

T1 validators6 read-only audit gates
T2 researchers10 read-only analysis
T3 implementers13 writes code/files
T5 orchestrators8 hub-and-spoke
# spawn from main session
Agent({
  subagent_type: "validator",
  prompt: "verify the 4 cites in...",
  isolation: "worktree"
})
$ filter --by=cat=allT1 · validatorT2 · researcherT3 · implementerT5 · orchestrator
[AGENT] · T5 · orchestratorread-only

architect

Senior software architect — analyzes structure, dependencies, patterns, data flow, coupling/cohesion. Read-only. Use for architecture review, system design, module-boundary analysis, pattern inventory, structural evidence-graded verdict.

[AGENT] · T5 · orchestratorread-only

cost-guardian

api-cost-guard.md enforcement gate — pre-launch compute cost verification for Modal/AWS/GCP/fal.ai/Apify/ElevenLabs. Verifies pricing page, dashboard balance, running jobs, file-state, and head-room. Read-only — emits GO/NO-GO recommendation BEFORE money is spent.

[AGENT] · T5 · orchestratorwrites

fal-ai-runner

fal.ai image, video, and 3D generation expert. Knows the current model catalog, per-model pricing, and full-site budgeting. Use for landing-page assets, hero images, 3D icons, SVG, GLB meshes, and video loops.

[AGENT] · T5 · orchestratorwrites

modal-runner

Modal compute orchestrator. Pre-launch cost estimation, GPU compatibility check, single-variant verify, observability-first, and a hard anti-stop guardrail against killing running training. Use for any Modal app launch, batch spawn, or job inspection.

[AGENT] · T5 · orchestratorread-only

security-auditor

Risk-classified (HIGH/MEDIUM/LOW) security audit with 9-point differential review, variant analysis, and supply-chain checks. Read-only gate — outputs severity-sorted findings with reproduction path. Hands fixes off to code-implementer.

[AGENT] · T5 · orchestratorwrites

security-auditor-differential

9-point differential security review. Auth bypass, injection, deserialization, race conditions. Read-only.

[AGENT] · T5 · orchestratorwrites

security-auditor-supply-chain

Supply-chain audit on new dependencies: maintainers, CVE history, transitive deps, native code. Read-only.

[AGENT] · T5 · orchestratorwrites

security-auditor-variant

Variant analysis after a vulnerability is found. Greps codebase for the same pattern. Read-only.

git-model (RULE 0.12)

# on fork, kei-ledger writes:
agent_id     = "a3f9c1..."
branch       = "agent/code-implementer-1714291200"
parent       = "feat/site-build"
spec_sha     = "sha256:7d2a..."
status       = "running"

# 6-file artefact bundle in .claude/agents/<id>/
spec.md     · plan.md     · progress.json
chatlog.md  · handoffs.md · review.md