distro-gentic

Plugin distro-gentic from marketplace distro-gentic in baristaze/distro_gentic. Commands read from the repo's manifest — 3 days ago.

Skills (47)

• audit-agent-levers

  Audit which levers an org's agents stalled after, in one environment: the agent playbooks its sessions invoked and the agent knowledge they recalled, ranked by how much more often the sessions that reached them stalled (a call made again and again, a call failing again and again, a request sent agai

• audit-credential-lifetimes

  Audit how long each credential keeps working after it should stop: one row per credential kind (auth session, API key, operator token, sign-in, socket ticket, and any other the code has) and channel (HTTP request, realtime socket, bus control message, worker), with where it is checked, how often, wh

• audit-database-calls

  Audit how many database calls each endpoint and each worker flow makes, at its least and at its most: round trips, transactions, and roles, counted at the driver while the real API and worker run in one process over a database of their own. Names what grows a flow, every N+1, every read repeated wit

• audit-deploy-time

  Audit where a deploy's minutes go: the pipeline's jobs and steps from the Actions run, the Terraform apply's resources, the migration's one-off task, each service's rollout from its ECS events, its tasks, and their first log lines, and the settings that pace them (health-check grace, container healt

• audit-matrix-spend

  Audit what the platform's model calls spend, in one environment, with a read-only credential: the spend by matrix version, the prompt tokens read from a cache, written to one, and sent uncached, the hit rate by matrix version, and what rebuilt caches cost, over a window; then a report with verdicts

• audit-model-spend

  Audit what an org's model calls spend, in one environment, from the usage records the engine wrote, read through the operator plane's usage route with a read-only operator token for the sessions named: the spend by agent kind, kind version, model role, and model, the prompt tokens read from a cache,

• audit-ontology-drift

  Audit, from the product's checkout, which concepts sit in a layer their nature contradicts. The product is an instance of the platform, which adopts the engine, which follows the guideline. The audit reads each layer at the release the product's base holds, down the scaffold branches' renders, and a

• audit-provider-calls

  Audit every call to an external provider (WorkOS, the AWS services, any HTTP to a third party), per flow: each route, inbound webhook, worker job, and boot. For each flow, the calls in order, whether they repeat or stand apart, whether they sit on the request path, how often the flow runs, whether t

• audit-query-indexes

  Audit whether the indexes fit the queries, and what breaks first under load: every statement the Postgres storage sends, mapped to the index that serves it and measured with EXPLAIN on a database of its own seeded at a stated scale, under the login and the tenant scope the application uses. Reports

• audit-retention

  Audit which stores grow without bound and what trims them: every table of every role, with what writes it, when a row is stale, the purge that deletes it, its retention, and whether that purge is batched and indexed; then the stores outside the database (log groups, buckets, queues, the cache). Meas

• docs-compact

  Compact the tree's documents to what holds at the head of the main branch: rewrite each ADR to its present decision with a status of one date, remove the ADRs that constrain nothing, cut the changelog to the latest release, clean the rows of specs/architecture.md, and rewrite the comments that tell

• ops-agent-session-spend

  Reconcile one session's model spend, in one environment, loop by loop, from the usage records the engine wrote: the session's rollup and each loop's, read once through the operator plane's usage route with a read-only operator token, then ops-loop-spend's reading over each loop, at most ten. Takes t

• ops-cloud-deployment-create

  Create one cloud environment of the system from nothing, in its own AWS account, as that account's administrator: the bootstrap root (state bucket, registry, OIDC trust, the deploy roles, the investigate role, the budget, the zones), the delegation of its public names at Cloudflare, the investigate

• ops-cloud-deployment-nuke

  Destroy one cloud environment of the system as its account's administrator: empty the buckets, destroy the environment root, remove what Terraform does not own (the secrets the application wrote, whose tenants' share follows the database's final snapshot, and the leftovers AWS made), and report what

• ops-host-idle

  Say why one workspace host of one tenant takes no work, in one environment: read its standing through the operator plane with a read-only operator token (its state, what it advertised, the version of work it reads against the floor, when it last called, and what is ready on its pool's lane and its o

• ops-infra-as-code

  Write or change the system's Terraform in the shape the guideline prescribes: one module graph shared by every environment, a variable for everything that differs, the autoscaling switch, the destroyable switch, the budget, the alarms, and the tags; then plan it under the read-only investigate profi

• ops-integration-silent

  Say why an integration went silent, in one environment, with a read-only credential: count what its inbound webhook route answered, read what the worker made of each delivery and the lines it logged, and read the webhooks queue and its dead letters, then report where the deliveries stop, why, and wh

• ops-investigate

  Investigate one environment of the system with a read-only credential: the alarms, the error rate, the latency, the outcomes, gauges, queues, and log lines each namespace's signals file names, the pool, the cost against the budget, and the system's size, then report what is wrong and what to do next

• ops-loop-spend

  Reconcile one loop's model spend, in one environment, from the usage records the engine wrote, read through the operator plane's usage route with a read-only operator token: each turn's tokens by class and its cost, the context's growth across turns, cache-miss streaks, compaction churn, and the cos

• ops-provider-outage

  Say which model provider and credential fail, in one environment, with a read-only credential: read the outage signal's reports and the line that names each provider and credential, and how many sessions park on a provider and for how long, then report the outage, its retry time, and its reach. Ever

• ops-root-cause

  Find the root cause of one tenant's problem in one environment: read that tenant's rows through the operator plane's read routes with a read-only operator token, correlate them with the logs, the trace, and the error event by request id, at most five ids and one pass each, and report the cause and t

• ops-session-stuck

  Say why one agent session of one tenant is not moving, in one environment: read its standing through the operator plane with a read-only operator token (its status and park, when it last changed, its loop's item, lease, lane, and place in line, its tenant's share, and where it runs), match it agains

• ops-simulate-traffic

  Drive realistic traffic at one environment of the system through its edge with the system's own traffic generator, at one of four profiles (light, regular, heavy, stress) for a duration, and report the table: requests by route and status, p50, p95, p99, and the error ratio. Use to warm an environmen

• ops-watch

  Watch one environment of the system live from a sub-agent: a log tail, the alarms as they fire, and the error and latency signals, batched per interval and capped, with a read-only credential. Run it in a sub-agent the invoking session spawns, because it polls for the whole window, at most 30 batche

• stress-test-create-or-update

  Write or edit one stress test scenario of the system, ops/stress/<name>.yaml: the profile, the duration, the ramp, the soak, the target p95 and error ratio, and the routes it weights. States what a good stress test has and refuses to write one without a target. Writes a file and nothing else; a run

• stress-test-run

  Run one stress test scenario of the system against one environment with the system's own generator, read the signals back through their own APIs, and report pass or fail against a target stated before the run: the scenario's p95 and error ratio, or the one the run states instead. A real run is the s

• tickets-triage

  Triage the open tickets whose subject is this repository: for each, read it and check it against the code on main, the merged and open pull requests, and the history, then give it a verdict (done, moot, partly done, still relevant, in flight, out of scope, unsure) with the evidence. Writes a report;

• distro-benchmark-browser

  Ask chatgpt.com, claude.ai, gemini.google.com, and grok.com, signed in, to judge this platform at its public URL with the browser-judge-distro prompt, and save each answer with its conversation URL as proof; in a checkout of this repository, also check the run in, redacted, with its row.

• distro-deviate

  Record a deliberate deviation from a rule of the distro_gentic spec as an ADR: the rule quoted, the decision, the consequences. Use when a finding of a platform review is accepted as intentional.

• distro-explain

  Explain how the distro_gentic spec applies to a question, a rule, a file, or a change, citing the sections and lenses that govern it and the reasons the spec gives. Use when onboarding to platform code or before a change that crosses its parts.

• distro-review-agent-fleet

  Platform review through the Agent Fleet lenses of the distro_gentic spec: The Agents a Platform Ships; Failure at Agent Fleet Scale; Operations. For a change in this area, or as one leg of distro-review-full.

• distro-review-evidence

  Platform review through the Evidence lenses of the distro_gentic spec: Evidence. For a change in this area, or as one leg of distro-review-full.

• distro-review-full

  Full platform review: the eight lens groups of the distro_gentic spec run in parallel beside the engine's and the guideline's full reviews, and the three layers merge into one report. Use before a pull request to platform code, or when a change crosses groups.

• distro-review-intake

  Platform review through the Intake lenses of the distro_gentic spec: Work In, Results Out. For a change in this area, or as one leg of distro-review-full.

• distro-review-money

  Platform review through the Money lenses of the distro_gentic spec: Money; Models Are an Agent Fleet Decision. For a change in this area, or as one leg of distro-review-full.

• distro-review-placement

  Platform review through the Placement lenses of the distro_gentic spec: Sessions Are Work; Agent Session Runners; Placement and Workspace Hosts. For a change in this area, or as one leg of distro-review-full.

• distro-review-wall

  Platform review through the Wall lenses of the distro_gentic spec: Trust; Data, Retention, and the Wall. For a change in this area, or as one leg of distro-review-full.

• distro-review-watch

  Platform review through the Watch lenses of the distro_gentic spec: Watching and Steering. For a change in this area, or as one leg of distro-review-full.

• distro-review-workspaces

  Platform review through the Workspaces lenses of the distro_gentic spec: Workspaces and Isolation. For a change in this area, or as one leg of distro-review-full.

• distro-scaffold-agent-automation

  Add an agent automation trigger: a kind of trigger beside the event and the schedule, fired by an occurrence a namespace records, with its filters on the trigger, its pure match rule, the work item that carries each occurrence to one firing, and its tests, so the limits, the own-events rule, and the

• distro-scaffold-agent-kind

  Add an agent kind the platform ships, or a new version of one: a profile over the engine's one loop with its tools, done rule, authority, workspace, policy layer, and model roles, in the shipped catalog every process builds from, with any tool of its own and its tests, in the shape of the platform's

• distro-scaffold-host

  Give the workspace host an isolation mode it probes but cannot run yet: the transport that runs a relayed tool call at that mode on the host's own disk, wired into the host's transports by mode, with its probe, its place among the owner's ceilings, and its tests, in the shape of the host's container

• distro-scaffold-integration

  Add a real client of an external system for one of the platform's integrations, with its twin: the signature check and the reading of a delivery into the platform's terms that both share, the client's posts, the twin's synthetic deliveries in the system's wire shapes, provenance on every record, the

• distro-scaffold-runner

  Add a session runner for a loop lane: the lane it claims (a plan tier's or a tenant's own), its process in the local stack, and its tests, the runner knowing the same agent kinds, tools, and domain classes as the product's API from the one declaration every process reads. Python.

• distro-scaffold-work-kind

  Add a product's own kind of work: its payload, the lane its payload names, the claimant kind that takes it through the gateway, with its program on the platform's claimant kit and its install through the one claimant installer with the kind's names and the groups it grants, and, when it needs them,

• distro-scaffold-workspace-provider

  Add a workspace provider: a backend that prepares, releases, and purges the workspaces a session's tools run in, at the isolation it can hold and refusing every other, paired with the transport that runs commands in what it prepares, selected by a setting a deployed process refuses when it cannot is

• distro-upgrade-scaffold

  Move a product's base to a later platform release: a product rendered from the platform's scaffold, or a layer that takes its scaffold/ folder unchanged. Runs the guideline's arch-upgrade-scaffold with the platform as its source, so one move takes all three foundations, and adds what the platform's

Subagents (1)

• distro-reviewer

  Reviews a scope of code through exactly one lens group of the distro_gentic spec and returns the standard review report. Used by distro-review-full to run the eight groups in parallel; can be delegated to directly with a group name, a scope, and the absolute paths of the lens file and the spec.

Similar plugins