From 54ad98b7cdc26de23a61297d9269f191e2f47fa0 Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:53:21 +0200 Subject: [PATCH 1/6] docs(plan): harness earns its place (pointer) Co-Authored-By: Claude Opus 5.5 --- docs/plans/2026-10-21-harness-earns-its-place.md | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 docs/plans/2026-10-21-harness-earns-its-place.md diff --git a/docs/plans/2026-10-21-harness-earns-its-place.md b/docs/plans/2026-10-21-harness-earns-its-place.md new file mode 100644 index 0000000..7adc644 --- /dev/null +++ b/docs/plans/2026-10-21-harness-earns-its-place.md @@ -0,0 +1,10 @@ +--- +canonical: decisions:docs/plans/2026-10-21-harness-earns-its-place.md +phases: [3] +status: done +--- +# A harness part earns its place on each model (pointer) + +The plan lives in decisions, which owns ADR-0042. This repository carries the +dotfiles half of Phase 3: each reviewer agent file states, in a `Catches:` +line, the failure its seat exists for (`harness.part-names-its-failure`). From b133cf5ee9c0d59ef627c0cecf8ea6f6a4d0b790 Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:53:31 +0200 Subject: [PATCH 2/6] docs(agents): each reviewer names its catch ADR-0042 harness.part-names-its-failure: a Catches line on every reviewer seat states the failure it exists for, so a review can ask whether the seat still catches it on the current model. Co-Authored-By: Claude Opus 5.5 --- dot_claude/agents/implementation-review.md | 2 ++ dot_claude/agents/interface-review.md | 2 ++ dot_claude/agents/plan-review-architect.md | 2 ++ dot_claude/agents/plan-review-backend.md | 2 ++ dot_claude/agents/plan-review-game-ux.md | 2 ++ dot_claude/agents/plan-review-language.md | 2 ++ dot_claude/agents/plan-review-platform.md | 2 ++ dot_claude/agents/plan-review-po.md | 2 ++ dot_claude/agents/plan-review-react.md | 2 ++ dot_claude/agents/plan-review-tui.md | 2 ++ dot_claude/agents/plan-review-ui-design.md | 2 ++ dot_claude/agents/plan-review-unix.md | 2 ++ dot_claude/agents/plan-review-ux-research.md | 2 ++ 13 files changed, 26 insertions(+) diff --git a/dot_claude/agents/implementation-review.md b/dot_claude/agents/implementation-review.md index caf75f2..abcd11f 100644 --- a/dot_claude/agents/implementation-review.md +++ b/dot_claude/agents/implementation-review.md @@ -3,6 +3,8 @@ name: implementation-review description: The one independent reviewer of an implementation before its push (ADR-0022, work.implementation-review). Reads the diff against the landed plan and the repository's active rules, reports findings only, never edits or waives anything. Launched by worktree-task F4b with a `<<>>` block; the amont-agent implementation-review hook checks at `git push` that it ran for the tree being pushed. tools: Read, Grep, Glob, LSP --- +Catches: a pushed change that departs from its approved plan, breaks an active rule, or adds a test that cannot fail. + You review an implementation before its author pushes it. You are not the author: you read and report. You never edit a file, never run anything, diff --git a/dot_claude/agents/interface-review.md b/dot_claude/agents/interface-review.md index 13aafe2..52d4f29 100644 --- a/dot_claude/agents/interface-review.md +++ b/dot_claude/agents/interface-review.md @@ -3,6 +3,8 @@ name: interface-review description: Independent interface reviewer of a change before its push, launched by worktree-task F4b step 2b. Follows ~/.claude/skills/interface-review/SKILL.md on the diff in its brief, reports findings only, never edits. tools: Read, Grep, Glob, LSP, mcp__duro-ds__duro_ds_lookup --- +Catches: an interface change that breaks accessibility, layout, copy or the design system's rules before the person sees it. + You review the interface side of a change before its author pushes it. You are not the author: you read and report. You never edit a file, never run diff --git a/dot_claude/agents/plan-review-architect.md b/dot_claude/agents/plan-review-architect.md index 683da64..61b6412 100644 --- a/dot_claude/agents/plan-review-architect.md +++ b/dot_claude/agents/plan-review-architect.md @@ -3,6 +3,8 @@ name: plan-review-architect description: Architect on a plan's review panel (ADR-0022, work.plan-review-panel), for large or long-lived repositories. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, LSP --- +Catches: a plan that puts a concept in the wrong module or tool, or couples parts that should stay apart. + You are a software architect reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-backend.md b/dot_claude/agents/plan-review-backend.md index b7ba518..09848bb 100644 --- a/dot_claude/agents/plan-review-backend.md +++ b/dot_claude/agents/plan-review-backend.md @@ -3,6 +3,8 @@ name: plan-review-backend description: Staff backend engineer on a plan's review panel (ADR-0022, work.plan-review-panel). Always part of the panel, and always re-runs on the final body and on every delta. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, LSP --- +Catches: a plan whose data flow, failure handling, concurrency or verification would not hold under real use. + You are a staff backend engineer reviewing a plan before its author presents it for approval. You are on every panel, and you are the reviewer diff --git a/dot_claude/agents/plan-review-game-ux.md b/dot_claude/agents/plan-review-game-ux.md index d492d86..80eca50 100644 --- a/dot_claude/agents/plan-review-game-ux.md +++ b/dot_claude/agents/plan-review-game-ux.md @@ -3,6 +3,8 @@ name: plan-review-game-ux description: Game developer and UX designer from the video game industry on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- +Catches: a plan whose interaction lacks the feedback, flow or recovery a player would expect. + You are a developer and UX designer from the video game industry reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-language.md b/dot_claude/agents/plan-review-language.md index 0a2f93c..ef2e2f4 100644 --- a/dot_claude/agents/plan-review-language.md +++ b/dot_claude/agents/plan-review-language.md @@ -3,6 +3,8 @@ name: plan-review-language description: Language expert on a plan's review panel (ADR-0022, work.plan-review-panel). Launched by /plan-review with a review block naming the language (lang=rust, lang=typescript, …). Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, LSP --- +Catches: a plan that fights the language's idioms, type system or toolchain, or names an API that does not exist. + You are a staff-level expert in the language named by `lang=` in the review block of your prompt (`<<>>`), reviewing a plan diff --git a/dot_claude/agents/plan-review-platform.md b/dot_claude/agents/plan-review-platform.md index c64507d..848fbac 100644 --- a/dot_claude/agents/plan-review-platform.md +++ b/dot_claude/agents/plan-review-platform.md @@ -3,6 +3,8 @@ name: plan-review-platform description: Staff platform engineer on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with Kubernetes, Flux, Helm or Terraform. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- +Catches: a plan that would break deployment, GitOps reconciliation, cluster resources or rollback. + You are a staff platform engineer reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-po.md b/dot_claude/agents/plan-review-po.md index ee9a573..6bf1f54 100644 --- a/dot_claude/agents/plan-review-po.md +++ b/dot_claude/agents/plan-review-po.md @@ -3,6 +3,8 @@ name: plan-review-po description: Product owner on a plan's review panel (ADR-0022, work.plan-review-panel), for large or long-lived repositories. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- +Catches: a plan that solves the wrong problem, misses the person's goal, or has no outcome anyone can observe. + You are a product owner reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-react.md b/dot_claude/agents/plan-review-react.md index bcb8adf..44ac5b5 100644 --- a/dot_claude/agents/plan-review-react.md +++ b/dot_claude/agents/plan-review-react.md @@ -3,6 +3,8 @@ name: plan-review-react description: React staff engineer on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, mcp__duro-ds__duro_ds_lookup --- +Catches: a plan whose React state, effects, rendering or component boundaries would misbehave. + You are a staff React engineer reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-tui.md b/dot_claude/agents/plan-review-tui.md index 315a460..2fae0c8 100644 --- a/dot_claude/agents/plan-review-tui.md +++ b/dot_claude/agents/plan-review-tui.md @@ -3,6 +3,8 @@ name: plan-review-tui description: TUI expert on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories that ship a command line: what a person sees and types. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- +Catches: a plan whose command-line output, prompts or terminal behaviour would confuse the person reading it. + You are a terminal UI expert reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-ui-design.md b/dot_claude/agents/plan-review-ui-design.md index 449ec10..21a69be 100644 --- a/dot_claude/agents/plan-review-ui-design.md +++ b/dot_claude/agents/plan-review-ui-design.md @@ -3,6 +3,8 @@ name: plan-review-ui-design description: UI designer on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, mcp__duro-ds__duro_ds_lookup --- +Catches: a plan whose visual hierarchy, spacing, color or type departs from the design system. + You are a senior UI designer reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-unix.md b/dot_claude/agents/plan-review-unix.md index 8278834..665669e 100644 --- a/dot_claude/agents/plan-review-unix.md +++ b/dot_claude/agents/plan-review-unix.md @@ -3,6 +3,8 @@ name: plan-review-unix description: Unix expert on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories that ship a command line. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- +Catches: a plan whose command line breaks Unix conventions: exit codes, streams, signals, flags or pipes. + You are a Unix expert reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-ux-research.md b/dot_claude/agents/plan-review-ux-research.md index 7c93862..cbad8fc 100644 --- a/dot_claude/agents/plan-review-ux-research.md +++ b/dot_claude/agents/plan-review-ux-research.md @@ -3,6 +3,8 @@ name: plan-review-ux-research description: UX researcher on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface: backs each UX choice with cited research or flags it as unbacked. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, WebSearch, WebFetch --- +Catches: a plan that makes a UX choice no cited research backs. + You are a UX researcher reviewing a plan before its author presents it for approval. From 0c50ad5974050b9f90f5aae87bceb6cd9247d9ab Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:54:45 +0200 Subject: [PATCH 3/6] docs(agents): Catches lines match each checklist Each sentence now names only failures its seat's own checklist covers; one blank line after it. Co-Authored-By: Claude Opus 5.5 --- dot_claude/agents/implementation-review.md | 3 +-- dot_claude/agents/interface-review.md | 1 - dot_claude/agents/plan-review-architect.md | 3 +-- dot_claude/agents/plan-review-backend.md | 1 - dot_claude/agents/plan-review-game-ux.md | 3 +-- dot_claude/agents/plan-review-language.md | 3 +-- dot_claude/agents/plan-review-platform.md | 1 - dot_claude/agents/plan-review-po.md | 1 - dot_claude/agents/plan-review-react.md | 1 - dot_claude/agents/plan-review-tui.md | 1 - dot_claude/agents/plan-review-ui-design.md | 3 +-- dot_claude/agents/plan-review-unix.md | 1 - dot_claude/agents/plan-review-ux-research.md | 1 - 13 files changed, 5 insertions(+), 18 deletions(-) diff --git a/dot_claude/agents/implementation-review.md b/dot_claude/agents/implementation-review.md index abcd11f..0237cf1 100644 --- a/dot_claude/agents/implementation-review.md +++ b/dot_claude/agents/implementation-review.md @@ -3,8 +3,7 @@ name: implementation-review description: The one independent reviewer of an implementation before its push (ADR-0022, work.implementation-review). Reads the diff against the landed plan and the repository's active rules, reports findings only, never edits or waives anything. Launched by worktree-task F4b with a `<<>>` block; the amont-agent implementation-review hook checks at `git push` that it ran for the tree being pushed. tools: Read, Grep, Glob, LSP --- -Catches: a pushed change that departs from its approved plan, breaks an active rule, or adds a test that cannot fail. - +Catches: a change about to be pushed that departs from its approved plan, records a check it cannot have run, breaks an active rule, or adds a test that cannot fail. You review an implementation before its author pushes it. You are not the author: you read and report. You never edit a file, never run anything, diff --git a/dot_claude/agents/interface-review.md b/dot_claude/agents/interface-review.md index 52d4f29..865e62b 100644 --- a/dot_claude/agents/interface-review.md +++ b/dot_claude/agents/interface-review.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob, LSP, mcp__duro-ds__duro_ds_lookup --- Catches: an interface change that breaks accessibility, layout, copy or the design system's rules before the person sees it. - You review the interface side of a change before its author pushes it. You are not the author: you read and report. You never edit a file, never run anything, and never approve on the author's behalf. diff --git a/dot_claude/agents/plan-review-architect.md b/dot_claude/agents/plan-review-architect.md index 61b6412..03ed775 100644 --- a/dot_claude/agents/plan-review-architect.md +++ b/dot_claude/agents/plan-review-architect.md @@ -3,8 +3,7 @@ name: plan-review-architect description: Architect on a plan's review panel (ADR-0022, work.plan-review-panel), for large or long-lived repositories. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, LSP --- -Catches: a plan that puts a concept in the wrong module or tool, or couples parts that should stay apart. - +Catches: a plan that puts a concept in the wrong module or tool, couples parts that should stay apart, or contradicts an active decision. You are a software architect reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-backend.md b/dot_claude/agents/plan-review-backend.md index 09848bb..c03f1da 100644 --- a/dot_claude/agents/plan-review-backend.md +++ b/dot_claude/agents/plan-review-backend.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob, LSP --- Catches: a plan whose data flow, failure handling, concurrency or verification would not hold under real use. - You are a staff backend engineer reviewing a plan before its author presents it for approval. You are on every panel, and you are the reviewer who re-reads the final body after the other reviewers' edits, so check that diff --git a/dot_claude/agents/plan-review-game-ux.md b/dot_claude/agents/plan-review-game-ux.md index 80eca50..35f2373 100644 --- a/dot_claude/agents/plan-review-game-ux.md +++ b/dot_claude/agents/plan-review-game-ux.md @@ -3,8 +3,7 @@ name: plan-review-game-ux description: Game developer and UX designer from the video game industry on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob --- -Catches: a plan whose interaction lacks the feedback, flow or recovery a player would expect. - +Catches: a plan whose interaction lacks the feedback, onboarding, flow or discoverability a player would expect. You are a developer and UX designer from the video game industry reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-language.md b/dot_claude/agents/plan-review-language.md index ef2e2f4..6054141 100644 --- a/dot_claude/agents/plan-review-language.md +++ b/dot_claude/agents/plan-review-language.md @@ -3,8 +3,7 @@ name: plan-review-language description: Language expert on a plan's review panel (ADR-0022, work.plan-review-panel). Launched by /plan-review with a review block naming the language (lang=rust, lang=typescript, …). Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, LSP --- -Catches: a plan that fights the language's idioms, type system or toolchain, or names an API that does not exist. - +Catches: a plan that fights the language's idioms, type system or toolchain, or claims behaviour no test would catch. You are a staff-level expert in the language named by `lang=` in the review block of your prompt (`<<>>`), reviewing a plan diff --git a/dot_claude/agents/plan-review-platform.md b/dot_claude/agents/plan-review-platform.md index 848fbac..2d23970 100644 --- a/dot_claude/agents/plan-review-platform.md +++ b/dot_claude/agents/plan-review-platform.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob --- Catches: a plan that would break deployment, GitOps reconciliation, cluster resources or rollback. - You are a staff platform engineer reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) diff --git a/dot_claude/agents/plan-review-po.md b/dot_claude/agents/plan-review-po.md index 6bf1f54..aa1c819 100644 --- a/dot_claude/agents/plan-review-po.md +++ b/dot_claude/agents/plan-review-po.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob --- Catches: a plan that solves the wrong problem, misses the person's goal, or has no outcome anyone can observe. - You are a product owner reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) diff --git a/dot_claude/agents/plan-review-react.md b/dot_claude/agents/plan-review-react.md index 44ac5b5..65c8742 100644 --- a/dot_claude/agents/plan-review-react.md +++ b/dot_claude/agents/plan-review-react.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob, mcp__duro-ds__duro_ds_lookup --- Catches: a plan whose React state, effects, rendering or component boundaries would misbehave. - You are a staff React engineer reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) diff --git a/dot_claude/agents/plan-review-tui.md b/dot_claude/agents/plan-review-tui.md index 2fae0c8..3a1dd2d 100644 --- a/dot_claude/agents/plan-review-tui.md +++ b/dot_claude/agents/plan-review-tui.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob --- Catches: a plan whose command-line output, prompts or terminal behaviour would confuse the person reading it. - You are a terminal UI expert reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) diff --git a/dot_claude/agents/plan-review-ui-design.md b/dot_claude/agents/plan-review-ui-design.md index 21a69be..7ff583c 100644 --- a/dot_claude/agents/plan-review-ui-design.md +++ b/dot_claude/agents/plan-review-ui-design.md @@ -3,8 +3,7 @@ name: plan-review-ui-design description: UI designer on a plan's review panel (ADR-0022, work.plan-review-panel), for repositories with an interface. Reviews a plan before it is presented; never edits anything. tools: Read, Grep, Glob, mcp__duro-ds__duro_ds_lookup --- -Catches: a plan whose visual hierarchy, spacing, color or type departs from the design system. - +Catches: a plan whose hierarchy, spacing, states or consistency departs from the design system. You are a senior UI designer reviewing a plan before its author presents it for approval. diff --git a/dot_claude/agents/plan-review-unix.md b/dot_claude/agents/plan-review-unix.md index 665669e..74a5e36 100644 --- a/dot_claude/agents/plan-review-unix.md +++ b/dot_claude/agents/plan-review-unix.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob --- Catches: a plan whose command line breaks Unix conventions: exit codes, streams, signals, flags or pipes. - You are a Unix expert reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) diff --git a/dot_claude/agents/plan-review-ux-research.md b/dot_claude/agents/plan-review-ux-research.md index cbad8fc..2eb3557 100644 --- a/dot_claude/agents/plan-review-ux-research.md +++ b/dot_claude/agents/plan-review-ux-research.md @@ -5,7 +5,6 @@ tools: Read, Grep, Glob, WebSearch, WebFetch --- Catches: a plan that makes a UX choice no cited research backs. - You are a UX researcher reviewing a plan before its author presents it for approval. Read the plan at the review block's `path` (`<<>>`) From 435b192d016334e0020e2a055c442ede2a8a15cc Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:54:47 +0200 Subject: [PATCH 4/6] feat(retro): flag a model no harness review covers ADR-0042: the weekly retro runs amont-agent harness-review --check and reports a model no review covers (exit 1 only; an older amont-agent adds nothing), and says when two model families are reviewed so the ADR's Revisit trigger can be checked. Co-Authored-By: Claude Opus 5.5 --- .../retro-weekly/executable_retro-weekly.sh | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/dot_claude/tools/retro-weekly/executable_retro-weekly.sh b/dot_claude/tools/retro-weekly/executable_retro-weekly.sh index 097c947..8ee8083 100644 --- a/dot_claude/tools/retro-weekly/executable_retro-weekly.sh +++ b/dot_claude/tools/retro-weekly/executable_retro-weekly.sh @@ -89,8 +89,29 @@ Sessions: $transcript" \ fi done +# ADR-0042 (harness.revisit-on-a-new-model): a model no harness review covers +# starts one. --check prints one line and exits 1 when that is so; any other +# status (2: an amont-agent too old to know the command) adds nothing. +harness='' +if command -v amont-agent >/dev/null 2>&1; then + out=$(amont-agent harness-review --check 2>&1) + if [ $? -eq 1 ]; then + harness="Harness: $out. Run \`amont-agent harness-review\` (ADR-0042)." + fi +fi +# ADR-0042's Revisit when: two reviewed model families and nothing retired. +reviews="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/amont-agent/harness-review" +models=$(cat "$reviews"/*.json 2>/dev/null | jq -r '.newest_model // empty' 2>/dev/null | sort -u | grep -c .) +if [ "${models:-0}" -ge 2 ]; then + harness="${harness:+$harness +}Harness reviewed on $models models: if ADR-0042's Log retires nothing, its Revisit trigger is met." +fi + { printf 'candidates: %s\n\n# Retro %s\n\n' "$total" "$(date +%F)" + if [ -n "$harness" ]; then + printf '%s\n\n' "$harness" + fi if [ "$reviewed" -eq 0 ]; then printf 'No session flagged by amont-agent in the last 7 days.\n' else From df7a0b18df82e6540cfa4facaecbf84c484e5834 Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:57:44 +0200 Subject: [PATCH 5/6] fix(retro): stdout only, name the family ceiling --check's stdout alone reaches the report; distinct model strings stand in for families under a holds-until; the weekly repeat is stated as intended. Fixture: two review files with different models print the Revisit line; the installed amont-agent without the command adds nothing. Co-Authored-By: Claude Opus 5.5 --- dot_claude/tools/retro-weekly/executable_retro-weekly.sh | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/dot_claude/tools/retro-weekly/executable_retro-weekly.sh b/dot_claude/tools/retro-weekly/executable_retro-weekly.sh index 8ee8083..d1485fa 100644 --- a/dot_claude/tools/retro-weekly/executable_retro-weekly.sh +++ b/dot_claude/tools/retro-weekly/executable_retro-weekly.sh @@ -94,12 +94,16 @@ done # status (2: an amont-agent too old to know the command) adds nothing. harness='' if command -v amont-agent >/dev/null 2>&1; then - out=$(amont-agent harness-review --check 2>&1) + out=$(amont-agent harness-review --check 2>/dev/null) if [ $? -eq 1 ]; then harness="Harness: $out. Run \`amont-agent harness-review\` (ADR-0042)." fi fi # ADR-0042's Revisit when: two reviewed model families and nothing retired. +# The line repeats every week once true, on purpose: it stands until the +# person checks the ADR's Log. +# holds-until: a review file records a model family; until then each distinct +# newest_model string counts as one, so a point release counts early. reviews="${CLAUDE_CONFIG_DIR:-$HOME/.claude}/amont-agent/harness-review" models=$(cat "$reviews"/*.json 2>/dev/null | jq -r '.newest_model // empty' 2>/dev/null | sort -u | grep -c .) if [ "${models:-0}" -ge 2 ]; then From c130b5b3d2ab37cddf8780fc32e466088cb7ea0d Mon Sep 17 00:00:00 2001 From: fredericrous Date: Thu, 22 Oct 2026 00:58:06 +0200 Subject: [PATCH 6/6] docs(plan): harness earns its place, phase 3 Co-Authored-By: Claude Opus 5.5 --- docs/plans/2026-10-21-harness-earns-its-place.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/docs/plans/2026-10-21-harness-earns-its-place.md b/docs/plans/2026-10-21-harness-earns-its-place.md index 7adc644..8a0ddaa 100644 --- a/docs/plans/2026-10-21-harness-earns-its-place.md +++ b/docs/plans/2026-10-21-harness-earns-its-place.md @@ -8,3 +8,7 @@ status: done The plan lives in decisions, which owns ADR-0042. This repository carries the dotfiles half of Phase 3: each reviewer agent file states, in a `Catches:` line, the failure its seat exists for (`harness.part-names-its-failure`). + +## Implementation review + +- Phase 3 (dotfiles): approve after two deltas. Fixed: five Catches sentences narrowed to what each checklist covers, one blank line each. Added: the weekly retro runs `harness-review --check` (exit 1 only) and says when two model families are reviewed (Phase 2's retro line and ADR-0042's Revisit owner), observed on a fixture. Deferred to decisions: interface-review.md in the plan's Phase 3 list.