intent-status

intent-status Skill

Core Mission

Shared temperature for matching checks (defined once here; each check refers to it as "shared temperature"): the orphan-spec / intent-tree-unfiled / Candidate / conformance matching checks are all done within what is machine-observable from files (Read/Glob/Grep only; git history and code diffs are not consulted), stay at candidate presentation, not an assertion, treat non-matchability as the normal case and tolerate false positives, and never take away the next-move first-match. When the target file is absent, the check is omitted (not an error).

• Success Criteria (success if achieved; the detailed check procedures are consolidated into Execution Steps, and only the outcomes are declared here):
  • The existence and fill state of the deliverables under .intent/ (mode, intent-tree, intent-compass, the packets index/files, the per-packet export drafts, deltas) are read and a summary of the current position is presented (read-only; never creates, modifies, or deletes any file)
  • Packets integrity (index ↔ active/ divergence, done / superseded_by lingering, the latest export-log row's packet absent from active/) is checked and violations are reported in the current-position summary
  • Orphan spec (no Packet) and intent-tree unfiled (discover skip) are reported in the details at the "shared temperature", and both plus writeback omission (downstream layer) are partitioned into three layers — tree layer → packet layer → downstream layer — with each spec presented only in the single most-upstream layer so no double warning is emitted
  • A leading mini progress rail (all packets laid out vertically with the five signals ✅/🔵/⚪/🔴/◻ plus [current stage → next stage(s) to pass through]) is placed at the top so "which packet is 🔵 you are here now, where the remaining work ⚪ / unreflected 🔴 are" is visible at a glance. Internal terms (matching, integrity check, enforcement) are pushed into the details
  • The default output is slimmed into three layers (default = one human decision + three separate readings + progress rail + Candidate count/names + a one-line Ice box notice / details = the folded position / option = only on a natural-language trigger), and the one-line summary of the next move is never folded and is always emphasized at the lead
  • The "dangerous notices" (freshness warning, packets integrity violations, unreflected 🔴) are shown in full as bare glyphs in the actual-impact context (never folded), with a one-line summary "⚠ N present (see details)" also left on the details side. In the explanatory context (legend, 0-count summary, etc.) they are toned down to inline code / words rather than bare glyphs (INV32)
  • The L4 "future addition candidates" that are unconsumed (neither packeted nor implemented) are presented as a permanent default display of count + names (frozen-marked ones excluded; "shared temperature")
  • Ice box candidates with a frozen mark are not shown in the body in the default; instead a one-line notice "Frozen (Ice box): N. Show them with 'show me the icebox'" is included, and on a natural-language trigger they are expanded as count + names + freeze reason
  • When a natural-language trigger such as "understanding map", "pre-start briefing", or "understanding gap sorting" appears, status preserves its read-only nature and guides the user to the corresponding /intent-overview derived views (.intent/overview/agent-understanding-map.md / active-packet-briefing.md / understanding-gaps.md)
  • Exactly one "next move" is recommended via the first-match of rules/decision-table.md (from discover / compass / packets / export / validate / improve / writeback / "no action needed"), accompanied by the reason and judgment basis. Only the presentation is changed; the first-match selection logic is untouched
  • When enforcement is remind / gate, a freshness check via intent-check is performed, and on a violation a freshness warning quoting the intent-check stdout is included (when off, unstated, an invalid value, or not executable, none is shown)
  • When drift-watch is on, drift-log is read and a light tally (prevented N / caught N / missed N / false-positive N / not-applicable N / unjudged N) is included (otherwise none; read-only)
  • The compass section update dates (Invariants / Decision Rules) and the active packets' updated_at are cross-checked, and when "not yet caught up after a compass update" reaches the threshold or more, /intent-validate is recommended as the right moment (decision table row 12; estimate only; "shared temperature")
  • When parallel-implementation claims exist (.intent/assignments/), the claimed packets, the double-claim warning on the same packet, and the stale-claim elapsed observation are included read-only (Step 3.8; with zero claims not included and unchanged from current behavior; warn-only; no machine threshold; "shared temperature")
  • Major terms in the output carry a one-line plain-language explanation in the term (explanation) form (two layers: lead = first occurrence / table headers only; details = every time; the glossary is kept and not abolished)