The design doc behind every feature.

• Agent busagent-bus.md

  Any agent on the machine leaves a message for any other agent, and Archie delivers it at a moment that is neither too early nor too late, exactly once, with the receiver told what…

  proposed 2026-09-07, not built.
• App-merge P3 — parity / kill duplicatesapp-merge-p3-parity.md

  From docs/specs/app-merge.md / #212:

  implementation merged (#218, #219, #222, #223, #225), checked 2026-10-0…
• App-mergeapp-merge.md

  This file is the durable home for the merge of apps/dashboard into apps/home. Code comments and PR bodies already name the phases; keep them honest here so a later session does no…

  product call locked 2026-09-30.
• Archie bencharchie-bench.md

  What #124 shipped, and what it did not. The local leaderboard is archie stats ladder and the stats_ladder MCP tool: the ladder with the API-equivalent spend below the evidence lin…

  the local table is built in #124; measured 2026-09-02.
• Archie — the memory agents do not havearchie.md

  MCP server shipped 2026-09-02 (#56); this spec's precondition is met.

  proposed.
• Asks: a questions-to-answers indexasks.md

  In a long session Saurabh asks a question. The answer lands several messages later, after tool calls, subagent notifications, and other assistant text — buried, not missing. He re…

  built, PR #97 (2026-09-02).
• Beliefsbeliefs.md

  AgentWorth already extracts what a session decided and verifies what it claims it did. It never checks whether a stated fact is still true. Give it a claim_check a session can cal…

  proposed, measured 2026-09-02.
• Cache economics — what returning cold actually costscache-economics.md

  A session's own logs already record what every turn paid to re-read its own history. Nobody surfaces it, so nobody learns from it. This spec turns that into a number a developer c…

  built, #42.
• CLI grammar, completions, and the cockpitcli-grammar.md

  Thirty-two top-level commands is a list, not a grammar. Nobody can guess blind-spots or cache-doctor from having used handoff. The fix is noun-then-verb: four nouns carry everythi…

  built: grammar #118, cockpit #121.
• Codex human turnscodex-human-turns.md

  Insights friction / day_hour / vocabulary read the human_turns table. That table is filled from harness prompt histories the session adapters do not own as "human input". Before t…

  built 2026-10-01 (PR #224).
• Compaction diffcompaction-diff.md

  Four things the build settled that this document left open:

  built, PR #83 (2026-09-02).
• Compaction, and what it costscompaction.md

  Measured on a real index of 612 sessions, not estimated.

  built, #57 (dashboard pane) and #62 (per-session tracking).
• Context composition — what fills the window before the work doescontext-composition.md

  Working name in conversation was "chewed". This document argues for context composition, on the grounds below.

  built, #46.
• Convergenceconvergence.md

  Where in a session the last verified progress happened, how much was spent after it, and whether anything that could fail ran at all.

  proposed, measured 2026-09-02.
• Desktop App — feasibility specdesktop-app.md

  Question this answers: would a Tauri wrapper around AgentWorth produce a working .dmg, what would that actually cost, and what has to be decided first.

  proposal, not started.
• The done gatedone-gate.md

  When a harness's agent is about to stop and say done, a plugin asks AgentWorth what evidence this session actually left, and if the answer is below the evidence line it hands the…

  proposed, measured 2026-09-03.
• Dropped commitmentsdropped-commitments.md

  An agent says it will do something and then does not. It is not lying; the intent was real when it was written and the conversation moved on. But the commitment is now in a transc…

  built, #44 and agentworth loose-ends.
• Efficiency receiptsefficiency-receipts.md

  Two weeks of local transcripts, four deterministic detectors, and a receipt per five-hour window saying which repeated work was provable, how long it sat in the window afterwards,…

  proposed, P0 measured 2026-09-02.
• AgentWorth / Evidence: the PR check (slice 1 of the evidence layer)evidence-check.md

  A developer pushes a branch. A pre-push hook signs a Work Receipt from the local index and pushes it as a git note. A GitHub Action named AgentWorth / Evidence verifies the signat…

  built, released in v0.
• The extension surfaceextensions.md

  AgentWorth does not become a coding harness. Archie reaches people as an extension inside the harnesses, shells, editors and pipelines they already run — and this is the ranked li…

  proposed, 2026-09-03.
• Fleet viewfleet-view.md

  Nobody can currently look at AgentWorth and answer "what's running right now, across everything on this machine." OverviewPane.tsx shows VerdictBoard (aggregate outcome distributi…

  built, #41 (fleet strip) and the SSE live-tail endpoint (v0.
• Governorgovernor.md

  Archie stops being the claims adjuster and becomes the governor: it meters every live session from its own transcript, tells the model what it is doing wrong with the receipt atta…

  built, PR #TBD (2026-09-06).
• Handoffhandoff.md

  The rest of this document is the design as measured on 2026-09-02.

  built, PR #TBD (2026-09-02).
• home latency: web deck vs terminal, measuredhome-latency.md

  Machine: MacBook Pro, Apple M1 Max, 32 GB RAM, macOS 27.0 (26A5425a). Deck build: apps/home at e1381ff (main, PR #152, "the elastic deck").

  measured 2026-09-07.
• homehome.md

  A local window where a founder runs 5 to 100 coding agents by setting directions and reading only what needs them.

  concept locked 2026-09-07, not built.
• Insights proxy naming (session user_messages ≠ human_turns)insights-proxy-naming.md

  Several /api/insights fields summed sessions.user_messages_count but were named as if they counted the human_turns table:

  built 2026-10-01 (honesty row #7).
• Local search and the small-model anglelocal-search.md

  Correction, verified 2026-09-01. An embedding pipeline already exists in this repo — crates/storage/src/{chunker,embedder,vector} and a working agwt search command. This spec was…

  draft spec, not yet built (mostly).
• Looploop.md

  Archie stops being a flight recorder that reads the tape afterwards and becomes the return path: the harness tells it what an agent is about to do, Archie records what actually ch…

  built, PR #TBD (2026-09-06).
• Loose endsloose-ends.md

  The command is agentworth loose-ends.

  proposed.
• Market map: observability that opens PRsmarket-autofix.md

  Research date: 2026-09-01. Every claim below is dated to what the cited page said on or near that date — pricing and positioning in this space change often. Where I could not veri…

• MCP servermcp-server.md

  The owner runs many long coding-agent sessions across several machines and repos. Every day he hand-writes handoff files so the next session knows what the last one did. A better…

  built.
• Machine memorymemory.md

  A fact that lives outside the context window cannot be compacted away. Archie stores memory as typed rows with receipts, an agent pulls the rows it needs by query, and markdown is…

  proposed 2026-09-08, measured.
• The questions worth answeringquestions.md

  Build the answers before designing screens for them. Most of these will turn out to be boring, and finding out which ones are boring is cheap.

  proposed.
• The AgentWorth and SpacePilot loopspacepilot-loop.md

  AgentWorth feeds SpacePilot's registry dream, and SpacePilot feeds AgentWorth's missing intelligence layer.

  direction, decided 2026-09-02; endpoints verified against spacepilot fc…
• Suspect commitssuspect-commits.md

  Shipped as the MCP tool suspect_commits and the CLI agentworth suspect, with agentworth suspect --hook printing the pre-push script. Two things changed between this spec and what…

  built, PR #84, measured 2026-09-02.
• Token accountingtoken-accounting.md

  Two separate things were wrong with the token numbers AgentWorth reports. One was a bug. The other is a definition that was never written down.

  built.
• Trajectory scrubbertrajectory-scrubber.md

  apps/dashboard/src/shell/TimelineStrip.tsx draws three rows of ticks (messages, model, tools) across the width of the inspector. Bucket count comes from measured container width,…

  built, #40.
• Verified outcome rateverified-outcome-rate.md

  Measured 2026-09-02, corrected the same day. Rung 3 used to be granted from the command string alone: is_test_or_build_command("cargo test") was true, so the session was recorded…

  proposed, measured 2026-09-02.
• Wakewake.md

  One tool call that tells a cold agent what it was doing, in under 30 lines, from the index and the checkout it is standing in.

  built, PR #TBD (2026-09-05).

39 files, read straight out of docs/specsSource on GitHub