adr-maintenance
Skill1.6k starsChanged todayMITView on GitHub
Create, update and supersede Overalls architecture decision records and reconcile implementation evidence with code. Use when architectural decisions change, a review finds design drift, implementation status changes, or the user asks to maintain ADRs, their index or architecture overview.
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Use decision status proposed, accepted, rejected or superseded separately from implementation planned, partial or implemented.
- Distinctive: line 31
Update the decision index in the same change, and the architecture overview when boundaries or the current implementation map change.
- Very specific: line 35
Run elixir scripts/check_adrs.exs from the root (or elixir ../scripts/check_adrs.exs from Marshall), then the component's required checks.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ADR maintenance
- Locate the repository root with
git rev-parse --show-toplevel. Read rootAGENTS.md,docs/architecture/decisions/README.md, relevant records and the actual changed code/configuration/tests. Read the review if one triggered this work. Separate observations, assumptions and unresolved choices. - Choose the smallest accurate update:
- Existing decision still holds: update facts, implementation evidence, open questions and implementation status in place.
- New decision: copy
docs/architecture/decisions/template.md, allocate the next unused ID, and fill every section with concrete rationale. - Material replacement of an accepted decision: create a new record. Preserve
the old rationale. Once the replacement is accepted, set the old status to
supersededand update bothSupersedesandSuperseded by. Keep history and historical implementation evidence. Before acceptance, describe the intended replacement through Related decisions without activating supersession.
- Use decision status
proposed,accepted,rejectedorsupersededseparately from implementationplanned,partialorimplemented. Existing explicit task/plan authorization can establish acceptance; do not request it again. Unresolved new choices stay proposed. Describe why alternatives were rejected and which properties verification must establish. - Link concrete implementation artifacts for partial/implemented claims and explain what each proves. Installed libraries, an accepted ADR or a planned test do not prove operational behavior. Mark remaining obligations explicitly; never mark a feature implemented merely to satisfy the checker.
- Update the decision index in the same change, and the architecture overview when boundaries or the current implementation map change. Add reciprocal supersession references and related links. Use the documented simple metadata and relative inline Markdown link syntax; avoid introducing a second template.
- Run
elixir scripts/check_adrs.exsfrom the root (orelixir ../scripts/check_adrs.exsfrom Marshall), then the component's required checks. Read failures and fix the actual records; do not weaken validation to conceal missing evidence or contradictions. The checker is structural only. - Summarize affected IDs, decision/implementation status changes, authorization
used, checks performed and any remaining questions. Use
$architecture-reviewwhen the change needs a substantive review.
Trending
Quiet since January.thin dataabout the whole repository
Who's talking about ghuntley/loom
- A Hacker News story“If your name is not Geoffrey Huntley then do not use loom”Hacker News · Jan 16, 2026 · 2 points
- daydemir/milhouse-go-legacy“Cross-Session Thread Loading & Replay (from Huntley Loom research)”GitHub · Jan 17, 2026
- daydemir/milhouse-go-legacy“Active System Verification Loops (from Huntley Loom research)”GitHub · Jan 17, 2026
- daydemir/milhouse-go-legacy“Meta-Loop Orchestration: Agents Spawning Sub-Loops (exploratory/major from Huntley Loom research)”GitHub · Jan 17, 2026
- daydemir/milhouse-go-legacy“Structured Audit Threads for Agent Decision Trails (from Huntley Loom research)”GitHub · Jan 17, 2026
The biggest 5 of 14 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 14
Talked about on GitHub and Hacker News (14 times).
On GitHub · 13
- Jan 17, 2026Cross-Session Thread Loading & Replay (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Active System Verification Loops (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Meta-Loop Orchestration: Agents Spawning Sub-Loops (exploratory/major from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Structured Audit Threads for Agent Decision Trails (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Server-Side LLM Proxy for Credential Isolation (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
8 more on GitHub
- Jan 17, 2026Secret Wrapper Type for Auto-Redacting (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Error Classification with Transient/Quota/Permanent (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Thread Persistence with UUID7 & Offline-First Sync (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Post-Tool Hook State for Auto-Commit (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Snippet-Based File Editing (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Proactive OAuth Token Refresh (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Multi-Account LLM Pool with Failover & Cooling (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
- Jan 17, 2026Explicit State Machine for Agent Orchestration (from Huntley Loom research) — daydemir/milhouse-go-legacy0 reactions
On Hacker News · 1
- Jan 16, 2026If your name is not Geoffrey Huntley then do not use loom2 points · 1 comment
In this repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- antithesis/AGENTS.mdAGENTS.md
- lilly/AGENTS.mdAGENTS.md
- marshall/AGENTS.mdAGENTS.md
- mila/AGENTS.mdAGENTS.md
- protocol/AGENTS.mdAGENTS.md
- susan/AGENTS.mdAGENTS.md
- antithesis-agent-browserSkill
- antithesis-debugSkill
- antithesis-documentationSkill
- antithesis-feature-workloadSkill
- antithesis-launchSkill
- antithesis-mutation-testingSkill
- antithesis-query-logsSkill
- antithesis-researchSkill
- antithesis-review-inputsSkill
- antithesis-setup-k8sSkill
- antithesis-setupSkill
- antithesis-skills-feedbackSkill
- antithesis-triageSkill
- antithesis-workloadSkill
- architecture-reviewSkill
- buck2Skill
- code-contractsSkill
- covenantSkill
- hegel-elixir-testsSkill
- localizationSkill
- monospace-webSkill
- nix-buildsSkill
- security-auditSkill
- test:triageSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

