BFM-decomp

a-slow-gate-is-a-bug.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

answer-before-grinding-in-live-coop.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

breadth-is-isolated-agents.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

checkpoint-means-everything-is-already-in-a-file.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

consult-the-tool-dictionary-first.md

tools+docs(phase-33.5): task 13.5 — the tools audit + the two dictionaries: tools/tool_census.py (two agreeing enumerations of 327 tool files; docstring/SETUP row/consumers/class derived from the tree; the authored half in config/tool_dictionary.tsv — phase · portability · the NEED each tool answers · what · adapts · verdict — with coverage asserted both ways) → docs/tool-index.md (need-keyed, KEEP-GEN, Reference-index row, wiki + how-to pointers), the kit's tools/MANIFEST.md regenerated (header states live 293 + superseded 28 = 321 rows), and the two verbatim corpora in-tree (Drew, confirmed S91): decomp-architect/corpus/tools/<phase>/ (302 copies + 28 superseded pointers + INDEX) and corpus/cookbook/ (the cookbook, its symptom index, the codegen map, a front page stating what transfers per compiler) — sha1-equal to their sources by tool_census --check in tools-health, regenerated by make kit-corpus; kit_lint exempts the corpus dirs (verbatim evidence) but syntax-checks them; G66 (consult the tool dictionary first) + G67 (translate an inherited idiom through its pass) + two memory seeds (34 at install); SETUP Step 6 installs docs/knowledge-corpus.md and checks the manifest against its own stated total; the ops-setup dictionary rows; the intake's Phase 7 cites G66/G67 and Phase 10 + Part C name the raw-cast → declared-symbol step; templates/layout-contract.md (the five-tool probe, a draft for the split). The review under Drew's criterion: 93 no-consumer tools (one Opus agent's draft, verified: 0 defects, every successor live, 0 live consumers, 0 collisions; four one-off verdicts overturned to STILL-NEEDED) → 34 retired by git mv to tools/sunset/ (28 superseded, 6 one-offs; README review table; SETUP rows moved; Archive-index group). Run 4 (fresh throwaway, the final kit): stopped on my Step-6 check (321 vs the live 293) → both sides derived → resumed → PASS 10/10, manifest 56 == 56, 4 commits, guardrails held (the one foreign path was the timeline regenerated by the detached tools-health). tools-health OK; doc_links --strict rc 0; audit_public OK over 6,842 paths; the purge probe PASSED (Phase 34's gate open). decision-log "P33.5 S91" + accelerators "P33.5 S91" banked; log + checkpoint (NEXT = task 14, xHigh, fresh session)

2026-09-07 22:09:15 -06:00

keep-an-accelerator-ledger.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

long-checks-run-in-the-foreground.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

mcp-reconnect-after-restart.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

MEMORY.md

tools+docs(phase-33.5): task 13.5 — the tools audit + the two dictionaries: tools/tool_census.py (two agreeing enumerations of 327 tool files; docstring/SETUP row/consumers/class derived from the tree; the authored half in config/tool_dictionary.tsv — phase · portability · the NEED each tool answers · what · adapts · verdict — with coverage asserted both ways) → docs/tool-index.md (need-keyed, KEEP-GEN, Reference-index row, wiki + how-to pointers), the kit's tools/MANIFEST.md regenerated (header states live 293 + superseded 28 = 321 rows), and the two verbatim corpora in-tree (Drew, confirmed S91): decomp-architect/corpus/tools/<phase>/ (302 copies + 28 superseded pointers + INDEX) and corpus/cookbook/ (the cookbook, its symptom index, the codegen map, a front page stating what transfers per compiler) — sha1-equal to their sources by tool_census --check in tools-health, regenerated by make kit-corpus; kit_lint exempts the corpus dirs (verbatim evidence) but syntax-checks them; G66 (consult the tool dictionary first) + G67 (translate an inherited idiom through its pass) + two memory seeds (34 at install); SETUP Step 6 installs docs/knowledge-corpus.md and checks the manifest against its own stated total; the ops-setup dictionary rows; the intake's Phase 7 cites G66/G67 and Phase 10 + Part C name the raw-cast → declared-symbol step; templates/layout-contract.md (the five-tool probe, a draft for the split). The review under Drew's criterion: 93 no-consumer tools (one Opus agent's draft, verified: 0 defects, every successor live, 0 live consumers, 0 collisions; four one-off verdicts overturned to STILL-NEEDED) → 34 retired by git mv to tools/sunset/ (28 superseded, 6 one-offs; README review table; SETUP rows moved; Archive-index group). Run 4 (fresh throwaway, the final kit): stopped on my Step-6 check (321 vs the live 293) → both sides derived → resumed → PASS 10/10, manifest 56 == 56, 4 commits, guardrails held (the one foreign path was the timeline regenerated by the detached tools-health). tools-health OK; doc_links --strict rc 0; audit_public OK over 6,842 paths; the purge probe PASSED (Phase 34's gate open). decision-log "P33.5 S91" + accelerators "P33.5 S91" banked; log + checkpoint (NEXT = task 14, xHigh, fresh session)

2026-09-07 22:09:15 -06:00

no-sleep-polling-background-tasks.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

offline-tooling-first.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

one-runbook-is-the-procedure.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

phaseend-carries-the-narrative-axis.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

resume-means-resume-the-run.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

route-by-measured-difficulty.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

the-byte-gate-is-the-only-claim.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

the-matching-flywheel.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

tool-change-ships-with-its-consumers-and-docs.md

docs(phase-33.5): task 9 — memory reconciliation + the kit's memory seed: decomp-architect/memory-seed/ (16 de-BFM'd seeds + MEMORY.md citing PA 2.0's own sixteen: the byte gate as the only claim, the matching flywheel, MCP reconnect, offline tooling first, a slow gate is a bug, breadth is isolated agents, route by measured difficulty, one runbook is the procedure, the accelerator ledger, checkpoint = already in a file, the PhaseEnd narrative axis, tool change ships with consumers + docs, no sleep-polling, long checks in the foreground, resume means resume the run, answer before grinding — five tagged upstream: PA); the project's own store outside git: the off-project memory parked, seven stale memories given dated update blocks, two index defects fixed (80 rows == 80 files); log + checkpoint

2026-09-07 18:10:00 -06:00

translate-the-source-idiom-through-the-pass.md

tools+docs(phase-33.5): task 13.5 — the tools audit + the two dictionaries: tools/tool_census.py (two agreeing enumerations of 327 tool files; docstring/SETUP row/consumers/class derived from the tree; the authored half in config/tool_dictionary.tsv — phase · portability · the NEED each tool answers · what · adapts · verdict — with coverage asserted both ways) → docs/tool-index.md (need-keyed, KEEP-GEN, Reference-index row, wiki + how-to pointers), the kit's tools/MANIFEST.md regenerated (header states live 293 + superseded 28 = 321 rows), and the two verbatim corpora in-tree (Drew, confirmed S91): decomp-architect/corpus/tools/<phase>/ (302 copies + 28 superseded pointers + INDEX) and corpus/cookbook/ (the cookbook, its symptom index, the codegen map, a front page stating what transfers per compiler) — sha1-equal to their sources by tool_census --check in tools-health, regenerated by make kit-corpus; kit_lint exempts the corpus dirs (verbatim evidence) but syntax-checks them; G66 (consult the tool dictionary first) + G67 (translate an inherited idiom through its pass) + two memory seeds (34 at install); SETUP Step 6 installs docs/knowledge-corpus.md and checks the manifest against its own stated total; the ops-setup dictionary rows; the intake's Phase 7 cites G66/G67 and Phase 10 + Part C name the raw-cast → declared-symbol step; templates/layout-contract.md (the five-tool probe, a draft for the split). The review under Drew's criterion: 93 no-consumer tools (one Opus agent's draft, verified: 0 defects, every successor live, 0 live consumers, 0 collisions; four one-off verdicts overturned to STILL-NEEDED) → 34 retired by git mv to tools/sunset/ (28 superseded, 6 one-offs; README review table; SETUP rows moved; Archive-index group). Run 4 (fresh throwaway, the final kit): stopped on my Step-6 check (321 vs the live 293) → both sides derived → resumed → PASS 10/10, manifest 56 == 56, 4 commits, guardrails held (the one foreign path was the timeline regenerated by the detached tools-health). tools-health OK; doc_links --strict rc 0; audit_public OK over 6,842 paths; the purge probe PASSED (Phase 34's gate open). decision-log "P33.5 S91" + accelerators "P33.5 S91" banked; log + checkpoint (NEXT = task 14, xHigh, fresh session)

2026-09-07 22:09:15 -06:00