Rynaro

Phase A (Abstract) — AgentFold compression of the Locate trajectory into a ≤2000-token working-memory summary plus a Memex excerpt store. Runs in a clean-context subagent to prevent trajectory contamination. Mechanically validates that every FINDING-XXX, GAP-XXX, and ESCALATION_TRIGGER is preserved. Use after findings.md is complete and before synthesis. Triggered automatically at phase boundary, or at ≥60% context-used telemetry threshold.

Phase L (Locate) — bounded probes and scatter subagents to answer DECISION_TARGET sub-questions. Descends a symbol → graph → lexical → windowed-read → test-dry-run ladder; emits FINDING-XXX records with evidence anchors and confidence tiers. Hot phase (≤60% of mission budget). Use after map.md is complete and sub-questions remain. Trigger phrases — "find where X happens", "trace Y", "who writes to Z", "who calls this", "what implements this".

Incremental delta re-scout (Phase A/T mode) — a READ-ONLY, evidence-anchored re-run that reuses a prior scout-report + its Memex store + a git-diff range to re-probe ONLY the changed surface, carrying unchanged findings forward verbatim. Narrows (does NOT close) the always-on-live-index staleness gap. Use at Phase A intake when a prior scout-report.md + Memex store exist for the same surface and the question is "what changed since the last scout" or "re-verify the prior map against HEAD". Do NOT use for a first-time scout (run the full A→T→L→A→S cycle instead).

Phase L sub-mode (Scatter-Gather Locate) — TRANCE-gated parallel fan-out of read-only Locate probes across topologically-disjoint module clusters, each in a clean-context subagent, merged back into findings.md via a deterministic dedup contract. Never default; serial Locate is the standard path. Use ONLY when map.md surface is large (>5 modules OR >25 files) AND ≥2 disjoint DECISION_TARGET sub-questions exist. Trigger phrases — "audit across all modules", "trace these N independent flows", "scout this large surface in parallel". Do NOT load for a single sub-question, tightly-coupled sub-questions, or a tight budget.

Phase S (Synthesize) — emit the scout-report.md artifact that downstream agents (SPECTRA, APIVR-Δ, human) consume. Hard cap 3000 tokens; every factual clause cited with FINDING-XXX; every recommended action carries a handoff label. Use after Phase A (Abstract) fold is validated and DECISION_TARGET has an answer or its gaps are recorded. Final phase of an ATLAS mission.

Phase T (Traverse) — deterministic structural mapping of a codebase. Zero LLM calls during retrieval; only symbol index, AST, ripgrep, and git log. Emits map.md with entrypoints, modules, call graph, and heatmap. Use after mission.md is valid and before any meaning-based search. Trigger phrases — "map the repo", "what are the entrypoints", "build the call graph", "list all routes/workers/CLIs".

Receiver-side ECL integrity gate (blocking, symmetric). Refuses to process any upstream artefact whose sibling .envelope.json lacks a verify_pass trace event from the orchestrator. Use when reading any upstream artefact handed off to ATLAS that carries a sibling .envelope.json. Symmetric across all Eidolons — every Eidolon enforces it identically per ECL §6.2.2.

Governs hypothesis generation, adversarial stress-testing, and multi-criteria scoring during the FORGE Reason phase. Use when the Reasoner enters Phase R to generate ≥3 distinct hypotheses, run Inversion/Boundary/Pre-Mortem/Dependency stress tests, score on a 5-dimension weighted rubric, and execute multi-pass deliberation. Do not use when Self-Consistency Mode (G2/TRANCE) is active — load forge-self-consistency instead.

ESL lifecycle hop — the DISCOVER hop. When a scout mission's findings surface change-worthy signal (a defect, a spec/impl drift, or a genuine gap) in an ESL-enabled project (.spectra/ present), ATLAS proposes opening an ESL change at 'proposed' by framing the scout-report + its ECL envelope it already emits as the proposal artifact — it never calls mcp__tonberry__* itself and never implements (refusal boundary intact). SPECTRA's own esl-hop owns the actual right_size/propose/specify tonberry calls on receipt, over the existing atlas-to-spectra handoff edge. Absent .spectra/ or absent change-worthy findings → hand off the scout-report normally (ESL opt-in).

Phase S (Synthesize) — emit the scout-report.md artifact that downstream agents (SPECTRA, APIVR-Δ, human) consume. Hard cap 3000 tokens; every factual clause cited with FINDING-XXX; every recommended action carries a handoff label. Use after Phase A (Abstract) fold is validated and DECISION_TARGET has an answer or its gaps are recorded. Final phase of an ATLAS mission.

Receiver-side ECL integrity gate (blocking, symmetric). Refuses to process any upstream artefact whose sibling .envelope.json lacks a verify_pass trace event from the orchestrator. Use when reading any upstream artefact handed off to ATLAS that carries a sibling .envelope.json. Symmetric across all Eidolons — every Eidolon enforces it identically per ECL §6.2.2.

Governs the checker-handoff gate for FORGE verdicts that authorize an irreversible action. Use at the end of the Emit phase, after the verdict and recommended action are drafted, to check the recommended action against the five mechanically observable irreversibility trigger markers (deploy/release, destructive migration or data deletion, security-boundary change, external spend/commitment, public communication). On a match, set the emitted reasoning-report's requires_checker flag to true instead of letting the verdict flow straight to execution. Reversible verdicts (no marker match) are unaffected — do not fire this skill for them.

Governs N perspective-diverse, mutually-blind reasoning traces with structural-agreement judge-merge for gated high-stakes FORGE decisions (G2/TRANCE). Use instead of forge-deliberation when Deep depth AND a stakes flag both hold (Framing score 8–9 with irreversible/system-wide blast radius), or on explicit opt-in. Do NOT use for standard-tier decisions — self-consistency is never the default.

Governs logic verification, evidence coverage, confidence calibration, and the REFORGE protocol during the FORGE Gate phase. Use when the Reasoner enters Phase G to check logical soundness (fallacy scan), verify evidence coverage, assess decision completeness, calibrate the 4-factor confidence score, and decide pass/emit or trigger a single REFORGE revision pass.

Phase A (Attest) result emission — finalizes the TaskState audit record with evidence-anchored claims, emits the mission result via ECL PROPOSE, and PROPOSEs any typed handoff-request UPWARD (never dispatches). Use when Grind reaches a terminal stop_state; load at the end of a GILGAMESH cycle. Do NOT use during Gauge/Inventory/Lock/Grind.

ESL lifecycle hop — in an ESL-enabled project (tonberry MCP available), when a fallthrough mission is authored as an ESL change, Gilgamesh is the MAKER and drives proposed→in_progress→(ready-for-verify). Gilgamesh NEVER self-verifies — maker≠checker is mechanically enforced (C4), so a distinct checker owns the verified transition. Absent tonberry → run the normal GILGAMESH cycle (ESL opt-in); never hard-fail.

SPECTRA v4 — vendor-agnostic specification and planning methodology for AI agents.

Implement typed async endpoint methods on ClickUpClient in clickup-api. Use this when creating or modifying files in clickup-api/src/endpoints/.

Create serde model structs for all ClickUp API entities in clickup-api. Use this when creating or modifying files in clickup-api/src/models/.

Build the core HTTP client with rate limiting, retry, and pagination in clickup-api. Use this when creating client.rs, rate_limiter.rs, or pagination.rs.

Implement authentication commands for clickup-cli. Use this when creating auth.rs, output.rs, or client_factory.rs in the CLI crate.

Implement space, list, and task browsing commands with rich output for clickup-cli. Use this when creating data browsing commands in the CLI crate.

Create documentation, issue templates, release workflows, and test suites for clickup-rs. Use this when preparing for release or writing project documentation.

Implement shared error types, config system, and token storage in clickup-api. Use this when creating error.rs, config.rs, or auth.rs in the API crate.

Load at the start of the APIVR-Δ Analyze phase. Techniques for building a repo map, running progressive disclosure, and maximising context relevance for coding tasks. Use whenever you need to understand unfamiliar code before editing it, or when an existing Discovery Report feels under-grounded.

Phase A (Abstract) — AgentFold compression of the Locate trajectory into a ≤2000-token working-memory summary plus a Memex excerpt store. Use after findings.md is complete and before synthesis. Runs in a clean-context subagent to prevent trajectory contamination. Mechanically validates that every FINDING-XXX, GAP-XXX, and ESCALATION_TRIGGER is preserved.

Phase L (Locate) — bounded probes and scatter subagents to answer DECISION_TARGET sub-questions. Use after Phase T (map.md) is complete. Descends a symbol → graph → lexical → windowed-read → test-dry-run ladder; emits FINDING-XXX records with evidence anchors and confidence tiers. Hot phase (≤60% of mission budget).

Phase S (Synthesize) — emit the scout-report.md artifact that downstream agents (SPECTRA, APIVR-Δ, human) consume. Use after Phase A (Abstract) fold is validated. Hard cap 3000 tokens; every factual clause cited with FINDING-XXX; every recommended action carries a handoff label.

Phase T (Traverse) — deterministic structural mapping of a codebase. Use when a mission.md brief exists and before any meaning-based search. Zero LLM calls during retrieval; only symbol index, AST, ripgrep, and git log. Emits map.md with entrypoints, modules, call graph, and heatmap.

Decision-ready specifications via the SPECTRA cycle. Use for complex features (complexity ≥7/12), multi-component/service changes, ambiguous requirements needing structured decomposition, or any task where 'just start coding' would require significant rework. Produces a dual-format spec (Markdown + YAML/JSON), never code.

Phase G (Graph) — build the Information Dependency Graph from candidate fault nodes. Distinguish propagated symptoms from root candidates using information flow, not temporal order. Rank root candidates by descendant count.

Phase I (Intervene) — falsify hypotheses via counterfactual replay. Design minimal interventions for each root candidate; run in sandbox; root cause is the one whose intervention flips failure→success. Hard cap 5 interventions.

Load at the start of the APIVR-Δ Analyze phase. Techniques for building a repo map, running progressive disclosure, and maximising context relevance for coding tasks. Use whenever you need to understand unfamiliar code before editing it, or when an existing Discovery Report feels under-grounded.

Load when the APIVR-Δ Verify phase produces failures — test fails, lint error, build break, or three consecutive unsuccessful attempts at the same category. Provides the failure classification taxonomy, bounded debugging protocol, and escalation thresholds. Use to avoid the 'random retries' anti-pattern.

Load at APIVR-Δ session start, session end, or when you notice a repeating pattern across tasks. Reflexion-style episodic memory protocol: read memory before planning; write after Verify and Reflect; consolidate at session end. Use to preserve learned patterns, failure classifications, and delta history across sessions.

Full APIVR-Δ cycle reference — A(nalyze) → P(lan) → I(mplement) → V(erify) → Δ(Delta)/R(eflect). Use when the task is a non-trivial feature implementation in a brownfield codebase and you need the complete methodology reference: complexity routing, evidence-grounded planning rules, test-anchoring requirements, and failure-escalation thresholds.

Load when reading any upstream artefact handed off by ATLAS (scout-report), SPECTRA (spec), VIGIL (root-cause-report), or FORGE (reasoning-report). Checks for a sibling .envelope.json, validates it against ECL v1.0 schemas, and appends a verify_pass or verify_fail trace event. WARN-ONLY on failure — the payload is always processed.

Decision-ready specifications via the SPECTRA cycle. Use for complex features (complexity ≥7/12), multi-component/service changes, ambiguous requirements needing structured decomposition, or any task where 'just start coding' would require significant rework. Produces a dual-format spec (Markdown + YAML/JSON), never code.

Decision-ready specifications via the SPECTRA cycle. Use for complex features (complexity ≥7/12), multi-component/service changes, ambiguous requirements needing structured decomposition, or any task where 'just start coding' would require significant rework. Produces a dual-format spec (Markdown + YAML/JSON), never code.

Pin an MCP server to a new version in the nexus catalogue (roster/mcps.yaml). Use when the user says "bump <mcp> to vX.Y.Z", "pin atlas-aci to 2.0.0", "crystalium shipped a release", "update the MCP catalogue", or after releasing an MCP server upstream. Covers digest capture and verification, backfilling skipped releases, the mcp_images.bats fixture coupling, CHANGELOG, the ESL change, and the verification gates. This is the MCP counterpart to `add-eidolon`, which covers Eidolons in roster/index.yaml — do not confuse the two.

Cut a release of the Eidolons nexus itself. Use when the user says "cut a nexus release", "release the nexus", "ship v2.4.0", or after merging changes that should be published. Covers the semver call, the VERSION/CHANGELOG cut, dispatching release-nexus.yml, and the integrity-metadata PR — which never gets CI, so you must verify it by hand. Distinct from `add-eidolon` (Eidolons) and `bump-mcp` (MCP servers), which release *other* things into the roster.

Pick the minimal bats test scope for a code change in the eidolons nexus before running tests. Maps changed paths (cli/src/*.sh, roster/, schemas/, methodology/, docs/, .github/) to the bats files that actually exercise them, and falls back to `make test` (full suite, ~41s) only when the change touches shared infrastructure (lib.sh, helpers.bash, the dispatcher, cli/src/ui/*, or anything ambiguous). Use when the user asks to run tests, when finishing an APIVR-Δ V-phase, or anytime you would otherwise reflexively run all 649 tests.

Promote an Eidolon to the nexus roster or bump an existing Eidolon's version. Use when the user says "publish X", "introduce X in the roster", "add X to the roster", "X is now stable", "bump <eidolon> to vX.Y.Z", or when working on a roster/index.yaml entry. Covers the full workflow — upstream repo normalization (EIIS-1.0 install.sh, version strings, CHANGELOG), roster + preset edits, capability-class schema changes for new classes, CI matrix, documentation touchpoints (README, MANIFESTO, composition.md, CHANGELOG), and verification.

ESL lifecycle hop — when the cortex routes a non-trivial change to SPECTRA in an ESL-enabled project (tonberry MCP available), SPECTRA owns the proposed→specify hop: right-size, propose the change folder, emit the spec into it. Absent tonberry → produce the spec normally (ESL opt-in).

Decision-ready specifications via the SPECTRA cycle. Use for complex features (complexity ≥7/12), multi-component/service changes, ambiguous requirements needing structured decomposition, or any task where 'just start coding' would require significant rework. Produces a dual-format spec (Markdown + YAML/JSON), never code.

Load when reading any upstream artefact handed off to SPECTRA that carries a sibling .envelope.json. BLOCKING per ECL §6.2.2: the orchestrator MUST have verified the envelope's SHA-256 (eidolons verify-envelope --block / eidolons run --verify) and recorded a verify_pass before dispatch. If no verify_pass exists for the message_id, or a verify_fail is present, REFUSE to process the payload and hand back to the orchestrator. Symmetric receiver gate — every Eidolon enforces it identically.

SPECTRA v4 — vendor-agnostic specification and planning methodology for AI agents.

Decision-ready specifications via the SPECTRA cycle. Use for complex features (complexity ≥7/12), multi-component/service changes, ambiguous requirements needing structured decomposition, or any task where 'just start coding' would require significant rework. Produces a dual-format spec (Markdown + YAML/JSON), never code.

Cut a release of the atlas-aci MCP server end-to-end. Use when the user says "release", "cut vX.Y.Z", "ship it", "run the release", or after a version's PRs are green and ready to land. Covers the merge-strategy decision, the version gate, tagging, watching the signed multi-arch build, capturing the image digest, archiving the ESL change (and the CI paths that breaks), and bumping the nexus catalogue.

Structured deliberation specialist. Produces evidence-grounded verdicts via the FORGE cycle (Frame → Observe → Reason → Gate → Emit). Use when a decision is genuinely hard — trade-offs with competing advantages, feasibility under tight constraints, root-cause analysis of complex failures, conflict resolution between agents or stakeholders, risk assessment of irreversible actions. Trigger whenever the user says 'should we', 'which is better', 'why did this fail', 'is this feasible', 'what are the risks', 'help me decide', or when upstream agents (SPECTRA, APIVR-Δ, ATLAS) escalate an unresolved decision. Also trigger for architecture decisions, technology selection, migration go/no-go, and any question where the answer requires weighing evidence rather than just retrieving it.

SPECTRA v4 — vendor-agnostic specification and planning methodology for AI agents.