mwguerra/plugins-haiku/big-context-analysis

Big-context analysis

A frontier model holds a whole corpus in one window; the executor here cannot. This skill replaces the one-window act with staged structure: every model invocation sees one attention-budget unit, every finding is a typed row on a durable blackboard, and no conclusion may be stated without citing finding ids a script verifies. Rationale: docs/plugins/analyst.md (marketplace repo).

The six phases

The finding schema (typed, dedup-keyed — the blackboard row)

Mappers never emit contradiction; that type is minted mechanically at merge when one (type, key) carries differing bodies, and from the merger's cross-input relations slot.

The conclusion slot card

Sizing (M1 — computed from countables, never self-sized)

Contradiction-dense board (contradictions × 20 > findings) bumps the tier to T3 at merge. Vote splits: T2 2–1 → +2 votes once; T3 ≥2 of 5 → one sonnet-class pass supersedes (M7 R2).

Laws (always in force)

1. One chunk per mapper invocation; one summary pair per merger invocation; one theme per

concluder invocation. No invocation ever loads the corpus whole.

1. Cite-or-die: a conclusion or strategy action citing an id that fails §CiteCheck is

laundering — the run halts; the text is never reworded past the check.

1. Conservation: every finding id in a merger's two inputs appears in exactly one output

theme; ids are never invented. jq-checked after every merge.

1. Checkpoint after every phase (§Checkpoint): artifacts to disk first, store rows second.
2. A failed phase blocks the run by construction (no v_next_step row) — report it;

never improvise past it.

1. A chunk failing map validation twice is logged in maps/*.failed, never silently

skipped; failed chunks × 10 > total chunks → halt.

Failure-mode absorbers

Files in this skill