hermes-quant

Step 1 of the hyperresearch V8 pipeline. Decomposes the canonical research query into atomic items, classifies pipeline_tier and response_format, and produces the coverage matrix that downstream steps depend on. The required_section_headings field this step produces is the single highest-leverage input for instruction-following scores. Invoked via Skill tool from the entry skill (hyperresearch).

Step 10 of the hyperresearch V8 pipeline. Orchestrator pre-curates 20-50 angle-specific source IDs per draft, then spawns 3 hyperresearch-draft- orchestrator subagents in parallel — each reads its curated list (no vault surveys, no source-fetching) and writes one angle-specific draft. This step ENDS when all 3 drafts are written and validated. Step 11 (synthesizer) handles the synthesis-write that produces the final report. For light tier: writes a single draft directly to final_report.md and skips ahead to step 15 (polish). Invoked via Skill tool.

Step 11 of the hyperresearch V8 pipeline. Reads the 3 angle-specific drafts from step 10, spot-checks factual conflicts, writes a synthesis plan + outline, then spawns ONE hyperresearch-synthesizer subagent (Read+Write tool-locked) that writes the final report in TWO passes — pass 1 rough integrated draft, pass 2 voice/redundancy/length cleanup. Skipped for light tier (which writes a single draft directly in step 10). Invoked via Skill tool from the entry skill (full tier).

Step 12 of the hyperresearch V8 pipeline. Spawns 4 adversarial critics in parallel against the synthesized final report from step 11. Each critic produces an independent findings JSON that the patcher (step 14) consumes. Critics never modify the draft directly. Invoked via Skill tool from the entry skill (full tier only).

Step 13 of the hyperresearch V8 pipeline. Conditional fetcher wave to fill vault gaps that critics identified. If a critic says "the draft ignored topic X" and the vault has zero sources on X, the patcher has nothing to cite. This step fetches the missing sources BEFORE patching so the patcher has ammunition. Capped at 5 gaps. Invoked via Skill tool from the entry skill (full tier).

Step 14 of the hyperresearch V8 pipeline. Spawns the hyperresearch-patcher subagent (TOOL-LOCKED to Read + Edit) to apply critic findings as surgical Edit hunks against the synthesized final report. Zero regeneration. Pre-stubs the patch log because Edit cannot create files. Handles orchestrator-escalated structural restructures inline. Invoked via Skill tool from the entry skill (full tier).

Step 15 (final) of the hyperresearch V8 pipeline. Spawns the hyperresearch-polish-auditor subagent (TOOL-LOCKED to Read + Edit) for the final hygiene + readability pass. Strips pipeline-reference leaks, YAML frontmatter, scaffold sections, filler phrases, run-on sentences. Escalates structural mismatches rather than fabricating content. Invoked via Skill tool from the entry skill. Followed by step 16 (readability audit) which is the actual final step before ship.

Step 16 (final) of the hyperresearch V8 pipeline. Spawns the hyperresearch-readability-recommender subagent (Read+Write tool-locked, Opus) to audit the polished final report and write JSON recommendations for paragraph merges, breaks, list/table conversions, bold injection, sentence splits, and HR removal. The orchestrator reads the recommendations and SELECTIVELY applies them via direct Edit calls (the recommender does NOT modify the report itself). Logs orchestrator decisions to a separate file. Runs for ALL tiers. Invoked via Skill tool from the entry skill.

Step 2 of the hyperresearch V8 pipeline. Multi-perspective search planning (breadth / depth / adversarial lenses) followed by parallel fetcher waves. Achieves comprehensive topical coverage with 40-100 curated sources for full tier. Includes coverage check, evidence redundancy audit, and source count gating. Invoked via Skill tool from the entry skill after step 1 completes.

Step 3 of the hyperresearch V8 pipeline. Builds an explicit graph of opposing claims across the corpus. Ranked fight clusters feed step 4's loci analysis so that loci emerge from where evidence actually forks, not from agent intuition. Also identifies consensus claims (3+ independent agreements) for confident assertion in the draft. Invoked via Skill tool from the entry skill after step 2 completes.

Step 4 of the hyperresearch V8 pipeline. Spawns 2 parallel loci-analyst subagents that read the width corpus and identify 1-6 specific questions where depth investigation will pay off. Deduplicates and scores each locus on importance/uncertainty/disagreement/decision_impact, then allocates source budgets dynamically. Invoked via Skill tool from the entry skill (full tier only).

Step 5 of the hyperresearch V8 pipeline. Spawns K depth-investigator subagents in parallel (one per scored locus), each producing one interim note with a Committed Position section. Investigators read full source bodies for their locus and may fetch additional sources within their source_budget. Invoked via Skill tool from the entry skill (full tier only).

Step 6 of the hyperresearch V8 pipeline. Reconciles the committed positions from all depth investigators into research/comparisons.md — 3-5 named cross-locus tensions with engagement guidance for the draft. This is the structural step that gives the single draft argumentative density. Invoked via Skill tool from the entry skill (full tier only).

Step 7 of the hyperresearch V8 pipeline. Extracts explicit expert disagreements from the corpus into research/temp/source-tensions.json, including orphan tensions that didn't surface as loci. Reads full source bodies of top 8-12 sources (not summaries) to find tensions that hide in nuance. The Source Tensions section in step 10's draft is the single highest-leverage move for insight scores. Invoked via Skill tool from the entry skill (full tier only).

Step 8 of the hyperresearch V8 pipeline. Spawns one corpus-critic subagent to identify "what source, if found, would overturn the current direction?" gaps, then runs a targeted fetch wave to fill them. Highest-leverage intervention point: corrections applied before drafting cost nothing; corrections applied after drafting require patches. Invoked via Skill tool from the entry skill (full tier only).

Step 9 of the hyperresearch V8 pipeline. Assembles the top load-bearing claims and verbatim quotes from the claims JSONs into research/temp/evidence-digest.md — a single high-fidelity evidence index the draft sub-orchestrators read as primary evidence (higher fidelity than fetcher summaries). Invoked via Skill tool from the entry skill (full tier).