EVA / prompt catalog
Each prompt is a self-contained artefact: metadata, body, examples, evals, and shell verbs in one place. 79 prompts across harness, rag, domain, and writing patterns.
ready · 49
-
auth-fail-open-auditv0.1.0 domainAuth fail-open audit
Hunts the specific shape where a dev-mode escape hatch becomes the production front door — an absent identity treated as "auth is off" rather than "the caller did not authenticate". Probes the running service without credentials.
-
fleet-host-rolloutv0.1.0 domainFleet-host rollout (hermes runner estate)
Executes install.sh across tenant roots on a shared multi-tenant fleet host — rollouts, runner version bumps, tenant onboarding. Encodes the two absolute refusals (never dockerd / the docker group; never rsync or hand-edit onto a tenant), demands provenance and a green estate suite before rolling, and refuses to accept a green checkmark as verification.
-
fleet-ingest-triagev0.1.0 domainFleet telemetry ingest triage (hermes)
Answers "is the fleet registered and is telemetry flowing?" in one call, then walks the ingest chain — webhook → org → run → job → fleet push — to the exact broken link. Codifies the orphan-job failure mode and the seam that caused it.
-
mcp-provider-wirev0.1.0 domainWire a REST API as an MCP provider (pebble flow)
End-to-end flow for exposing an existing HTTP API as MCP tools through the pebble gateway — config, self-disable, registry dispatch, corpus entry, tests, and the two traps that mocked tests cannot catch (wrong auth scheme, wrong route).
-
pebble-toolsv0.1.0 domainFleet tools via the PEBBLE gateway
Discover and call fleet MCP tools (petrova, ares, hermes, traceo, github, Proof KB, …) through the one authenticated PEBBLE gateway at mcp.devarno.cloud, using the live /registry + session profiles.
-
petrova-adr-tradeoffv0.1.0 domainPETROVA ADR with trade-off framework
Architectural decision review — enumerate pains, options, rejection reasons, chosen + accepted trade. Drafts a decision doc.
-
petrova-autopilotv0.1.0 harnessPETROVA autopilot (lifecycle outer loop)
Reads readiness, picks the next petrova verb, dispatches via kick, and chains until DONE or operator gate.
-
petrova-bootstrapv0.1.0 domainPETROVA bootstrap (Day 1)
Bootstrap a bare-bones consumer repo into petrova shape (CLAUDE.md, MILESTONES.md, AGENTS.xml, docs/ scaffold).
-
petrova-boundary-auditv0.1.0 domainPETROVA boundary + privileged-path audit
Where can scripts/agents write to sensitive surfaces (workflows, secrets, IAM, db) without going through a reviewable PR? Propose typed verb gates.
-
petrova-changes-sincev0.1.0 domainPETROVA changes-since
What changed since {{since}} — git log + file deltas grouped by area, with intent summaries and privileged-path flags.
-
petrova-decision-docv0.1.0 domainPETROVA decision doc (ADR)
Author a dated, append-only decision doc at docs/decisions/YYYY-MM-DD-`slug`.md (MR-7).
-
petrova-declare-baselinev0.1.1 domainPETROVA declare baseline
Ratify a new fleet baseline (v2, v3, ...) as a decision doc in petrova-codes; verb pre-flight refuses if any MR audit check fails.
-
petrova-doc-freshnessv0.1.0 domainPETROVA doc freshness audit
Flag every docs/ file whose claims are now wrong because the underlying code changed and the doc didn't (MR-12 enforcement).
-
petrova-doctorv0.1.0 domainPETROVA doctor (preflight)
Read-only preflight — submodules, contract, registry entry, branch protection. Emits structured readiness JSON for petrova-autopilot.
-
petrova-drift-checkv0.1.0 domainPETROVA drift check
Probe rank-graph contradictions and named anti-shape drift; surface or resolve.
-
petrova-failure-triagev0.1.0 domainPETROVA failure-mode triage
Map an observed error/symptom to the closest PETROVA error code and prescribe the runbook recovery path adapted to this stack.
-
petrova-findingv0.1.0 domainPETROVA finding
Emit a raw finding at docs/findings/YYYYMMDD-HHMM-`slug`.md.
-
petrova-fleet-snapshotv0.1.0 domainPETROVA fleet snapshot
Produce or refresh fleet_snapshot.yaml for a slug from registry + remote state.
-
petrova-friction-classifyv0.1.0 domainPETROVA friction classifier
Classify a friction item: closed (trivial follow-up) / in-budget (small, lands now) / deferred (next-phase milestone — MR-2). When in doubt, defer.
-
petrova-governance-inventoryv0.1.0 domainPETROVA governance inventory
Read-only governance scan: surface every governance signal in this repo and gap-rate against PETROVA.
-
petrova-health-checkv0.1.0 domainPETROVA health check (5-dimension)
Five-dimension health snapshot: build, tests, docs freshness, decision-doc velocity, drift signals. Letter grade A–F.
-
petrova-install-playbookv0.1.1 domainPETROVA install playbook
Step 0 of consumer onboarding. Deposit the petrova playbook (META-RULES.md, 00-bootstrap.md, partials, progress schema) into a consumer repo's `.petrova/playbook/` so subsequent bootstrap prompts can resolve `{{...}}` references against literal local paths.
-
petrova-invariant-soakv0.1.1 domainPETROVA invariant soak
Runs an assertion table from the cycle.yaml against a staging slice. Each row is one project invariant (I-N) with a probe that yields pass | fail | skip.
-
petrova-milestone-addv0.1.0 domainPETROVA milestone add
Append a milestone entry to MILESTONES.md (used to land MR-2 deferred items).
-
petrova-mr-checkv0.1.0 domainPETROVA MR-1..15 audit
Audit a consumer repo against every meta-rule; emit a violations list and a progress signal.
-
petrova-north-star-alignv0.1.0 domainPETROVA north-star alignment audit
Sample recent commits/PRs and judge whether each served the north-star, load-bearing infra, or backlog (MR-1 enforcement).
-
petrova-onboardv0.2.1 domainPETROVA onboard
Initialise a registered consumer repo's mechanical petrova floor — write `.petrova/contract.yaml` + install the `docs-invariants` workflow, via the `petrova_onboard` verb.
-
petrova-phase-closev0.1.0 domainPetrova Phase Close
petrova-phase-close
-
petrova-phase-openv0.1.0 domainPetrova Phase Open
petrova-phase-open
-
petrova-plan-featurev0.1.0 domainPETROVA plan a feature
Translate a feature ask (vague or specific) into PETROVA-shaped scope: north-star sentence, tasksets with deliverable+verification+gate, reuse-first.
-
petrova-post-mortemv0.1.0 domainPETROVA post-mortem from audit trail
Reconstruct the trigger chain over a window from commits/PRs/CI, name where the audit trail had gaps, output what would have prevented this.
-
petrova-propose-fixv0.1.1 domainPETROVA propose fix
Open a fix PR bound to a prior diagnose run. Validates that the diagnosis_id resolves to a real recent diagnose output and that every proposed change carries explicit MR grounding.
-
petrova-request-merge-when-greenv0.1.1 domainPETROVA request merge when green
Open a PR with auto-merge enabled. Profile-gated — only repos with branch protection that permits auto-merge can use this verb. Validates merge_method and grounding before composing the PR envelope.
-
petrova-request-reviewv0.1.1 domainPETROVA request review
Open a PR with explicit file changes and request human review. Validates operator-supplied grounding (decision docs, MR citations, north-star refs) before composing the PR envelope.
-
petrova-routine-archaeologyv0.1.0 domainPETROVA routine archaeology
Read-only scan that surfaces manual operations worthy of becoming Claude Code Routines; emits ranked candidate specs.
-
petrova-stalled-workv0.1.0 domainPETROVA stalled-work scan
Find PRs without recent activity, milestones not progressing, decisions open `14 days, findings without paired decisions, branches `30 days unmerged. Group: revivable / blocked / abandoned.
-
petrova-supersession-checkv0.1.0 domainPETROVA supersession check
Find every closed-status decision doc whose claims a proposed change would contradict; draft Supersedes: docs (never edits originals — MR-7).
-
petrova-upstream-watchv0.1.1 domainPETROVA upstream watch
Generic upstream-source poller. Cycle author declares the sources (PyPI, GitHub releases, RSS) and notify rules; this prompt classifies deltas as none | minor | breaking | unknown and routes escalations.
-
petrova-verify-roundv0.1.0 domainPETROVA verification round
Run the mandatory friction-probe verification round for an open phase (MR-10).
-
petrova-wire-aresv0.2.0 domainPetrova Wire Ares
Draft the ARES wire-decision doc and describe the manual contract.yaml evidence-block update; no dedicated wire-verb exists in petrova-codes.
-
petrova-wire-contract-driftv0.1.1 domainPETROVA wire-contract drift
Walks a contract repo (e.g. proto-schemas) HEAD against every consumer's gen/ checksum. Surfaces silent schema drift before it surfaces as a confusing build error.
-
petrova-wire-integrationv0.1.1 domainPETROVA wire integration
Flip a registered consumer's `.petrova/contract.yaml` integration block from pending → wired with a validated evidence object. Generic over ares/traceo/crumb/rocky/eva.
-
petrova-wire-traceov0.2.0 domainPetrova Wire Traceo
Draft the TRACEO wire-decision doc and describe the manual contract.yaml evidence-block update; no dedicated wire-verb exists in petrova-codes.
-
refactor-with-constraintsv1.4.0 domainRefactor with Explicit Constraints
Surgical refactor of a single file under named constraints; produces diff + rationale + risks.
-
session-handoffv0.1.0 domainSession handoff (agent → agent)
Writes the handoff a fresh agent can actually act on — verified facts separated from beliefs, the exact commands that produced them, what is deployed vs merged vs open, and what is still UNPROVEN. Refuses to hand over false greens.
-
task-acceptance-checkv0.1.1 writingTask acceptance check
Read-only verifier. Given a Task and a candidate completion artefact, scores each acceptance criterion line-by-line. Output is a structured pass/score block consumed by `tasks/complete`.
-
task-bundle-plannerv0.1.1 harnessTask bundle planner
Decompose a goal + acceptance criteria into a TaskBatch — a structured queue of single-pass tasks, each grounded in a /map node with pre-bound args. Used by `eva tasks sync` to populate the EVA task backlog.
-
verify-email-flow-harnessv0.1.0 domainVerify end-to-end email flow for any app
Plug-in e2e verification of magic-link email flow — dispatch, Resend outbox poll, click-through in headless Chromium, session assertion. Generic over app base URL, dispatch path, and probe email.
-
verify-for-realv0.2.0 domainVerify for real (anti-false-green)
Refuses the ways a green signal lies — exit code from the wrong process, a cancelled job read as a pass, a suite that is green because of the bug, a suite that collected zero tests, "tests pass" mistaken for "it works", and a broken measurement reporting absence as a clean negative. Drives the real system before any completion claim.
tested · 2
-
handbook-section-generatorv0.5.0 writingGenerate a Handbook Section from Notes
Synthesises bullet-form notes into a named handbook section in a chosen voice; surfaces contradictions.
-
orchestrate-multistepv0.3.0 harnessMulti-step Orchestration Executor (autopilot-shaped)
Executes one step of a JSON plan; emits strict-JSON handoff with predict/wake/learn fields per autopilot loop semantics.
draft · 28
-
brand-asset-generatorv0.1.0 writingBrand Asset Generator
Read BRAND.md + PRODUCT.md and emit a complete BRAND_ASSETS.md with image-gen prompts, palette, and typography for every named surface.
-
crumb-extraction-harnessv0.1.0 domainCRUMB Extraction Harness
Harness-pattern orchestrator that fans out background subagents across {{target_repos}}, dispatching the crumb-flashcard-extractor per repo with Ruflo memory/KG/intelligence enrichment and autopilot-shaped JSON handoff.
-
crumb-flashcard-extractorv0.3.1 writingCRUMB Flashcard Extractor
Scan a source repository and emit CRUMB-schema flashcards (20-field strict frontmatter, mermaid-first diagrams) ready to drop into crumb.devarno.cloud.
-
downlink-entry-authorv0.1.0 writingDOWNLINK Entry Author
Turn raw notes or a draft artefact into an abacus blog-post markdown file that projects onto devarno.com/downlink cleanly on the first try.
-
downlink-publishv0.1.0 harnessDOWNLINK Publish
Project abacus blog entries onto landing and verify the result, or check for drift between the two repos without touching anything.
-
downlink-social-repurposerv0.1.0 domainDOWNLINK Social Repurposer
Turn a shipped DOWNLINK entry into a platform-native social artefact (X thread, LinkedIn post, Bluesky post, or newsletter excerpt) through a per-platform lens.
-
eva-askv0.1.0 domainEVA ask — evidence-bound RAG answer
Answer a question with an evidence-bound RAG pipeline; emit answer, evidence, and a validator verdict. Refuses-with-gap on insufficient evidence.
-
eva-baselinev0.1.0 domainEVA baseline — ratify a new fleet baseline
Ratify a new fleet baseline after an all-PASS health pre-flight; declare the baseline with the live audit snapshot embedded. Refuses if the audit is red.
-
eva-cyclev0.1.0 domainEVA cycle — phase-boundary chain
Run the phase-boundary chain (verify-round → phase-close → optional phase-open); halt at first FAIL and draft a decision doc if an invariant slipped.
-
eva-flowv0.1.0 domainEVA flow — plan, queue, and execute one step on a goal
Plan→Queue→Execute on a goal; plan the feature, emit an eva-task-batch, and advance exactly one step with a strict-JSON envelope.
-
eva-healthv0.1.0 domainEVA health — read-only governance gauntlet
Run the read-only governance gauntlet (doctor, drift, boundary, invariant, MR, supersession) and emit one PASS/WARN/FAIL table with evidence.
-
eva-nextv0.1.0 domainEVA next — predict the highest-leverage next prompt
Read EVA workflow state + fleet.context and pick the single highest-leverage next prompt; emit the dispatch envelope. Does not invoke.
-
eva-onboardv0.1.0 domainEVA onboard — bring a fresh repo into the fleet
Bring a fresh repo into the fleet end-to-end via the bootstrap prose flow, the operator registry-PR gate, and an idempotent onboard resume.
-
eva-projectv0.1.0 domainEVA project — re-project HANDBOOK.md + command-manifest.json
Re-project the handbook + command-manifest pair from the live catalogue. The only writer of the pair.
-
eva-recoverv0.1.0 domainEVA recover — failure response on the latest red signal
Respond to the latest red signal — triage the failure, draft a decision doc with ≥2 alternatives, then plan the fix with halt gates and a verification round.
-
eva-tickv0.1.0 domainEVA tick — one governed petrova-autopilot iteration
Run a single governed petrova-autopilot iteration; pick and kick the next petrova verb and emit a progress_signal with predict_next and wake_seconds.
-
impeccable-handbook-generatorv0.1.0 writingImpeccable Handbook Generator
Inspect a freshly /impeccable-onboarded project and emit a project-specific IMPECCABLE_HANDBOOK.md plus skeleton sidecar.
-
impeccable-harness-executorv0.3.0 domainImpeccable Harness Executor
Deterministic orchestrator that drives an IMPECCABLE_HANDBOOK.md to completion via Claude Code Task() sub-agents.
-
meta-prompt-generatorv0.1.0 writingMeta-Prompt Generator (implementation-prompt architect)
Transforms "I want to do task X" into a rigorous, subagent-driven implementation prompt for a downstream coding agent — ground-truth-first, phased, diff-evidenced.
-
petrova-wire-crumbv0.2.0 domainPetrova Wire Crumb
EXPERIMENTAL — describe intended CRUMB wiring shape; no backing verb in petrova-codes yet.
-
petrova-wire-evav0.2.0 domainPetrova Wire Eva
EXPERIMENTAL — describe intended EVA prompt-library wiring shape; no backing verb in petrova-codes yet.
-
petrova-wire-rockyv0.2.0 domainPetrova Wire Rocky
EXPERIMENTAL — describe intended ROCKY RAG wiring shape; no backing verb in petrova-codes yet.
-
rag-chunk-rerankerv0.1.0 ragRAG Chunk Reranker (LLM-as-reranker with MMR diversity)
Reranks candidate chunks against a query, balancing relevance and MMR-style diversity; preserves input ids.
-
rag-context-synthesizerv0.1.0 ragRAG Context Synthesizer (cited answer with coverage report)
Composes a grounded answer from id-keyed chunks; cites by id; refuses on insufficient evidence.
-
rag-evidence-validatorv0.1.0 ragRAG Evidence Validator (faithfulness · groundedness · citation audit)
Audits a RAG answer against its source chunks; pairs each claim to supporting ids and flags unsupported spans.
-
rag-query-rewriterv0.1.0 ragRAG Query Rewriter (expand · decompose · HyDE)
Rewrites a user query for retrieval — expansion, decomposition, or HyDE — emitting a strict JSON plan.
-
repo-dag-executorv0.2.0 harnessRepo Audit DAG Executor
Drive a shell-script harness that dispatches Claude Code Task sub-agents against an audit DAG until every node verifies green.
-
repo-dag-generatorv0.1.0 writingRepo Audit DAG Generator
Audit a repository and emit state.md + graph.md + per-node prompts/*.md — the execution plan for a fleet of agents to finish the repo.
no matches.