Borrowing it
Nothing to install: this file belongs to harumiWeb/exstruct. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/harumiWeb/exstruct/main/.agents/skills/adr-reviewer/SKILL.mdgit clone --depth 1 https://github.com/harumiWeb/exstructWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/harumiweb/exstruct/adr-reviewer)<a href="https://agentmods.dev/skills/harumiweb/exstruct/adr-reviewer"><img src="https://agentmods.dev/badge/skills/harumiweb/exstruct/adr-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/harumiweb/exstruct/adr-reviewer"><img src="https://agentmods.dev/badge/skills/harumiweb/exstruct/adr-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00066 | $0.00614 |
| Opus 5.5 | $0.00026 | $0.00246 |
| Sonnet 5.5 | $0.00013 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
Grade A, and why
adr-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Reviewer
Review the policy decision, not just the document shape.
Read
dev-docs/agents/adr-governance.mddev-docs/agents/adr-criteria.mddev-docs/agents/adr-workflow.mddev-docs/specs/adr-review.md- The target ADR draft
- Related ADRs, relevant public docs under
docs/when public API / CLI / MCP contracts are in scope, internal specs, tests, src paths, and issue / PR context - Existing
adr-linterfindings for the current draft
Workflow
- Confirm the current draft has no unresolved
adr-linterhigh/mediumfindings. Only proceed with design review after that precondition is met. - Read the ADR draft and identify the single policy question it is trying to resolve.
- Check whether the draft overlaps with, contradicts, or should supersede an existing ADR or spec.
- Verify that the cited
Tests,Code, andRelated specsactually support the claims being made, and include relevant publicdocs/pages in scope when the ADR touches public API / CLI / MCP contracts. - Review whether compatibility, rollout, fallback, migration, or safety consequences are covered when relevant.
- Detect human-owned decisions that AI should not settle, including public API break judgment, security or license calls, major directory reorganization, or unresolved product/spec direction.
- Return one verdict:
readyreviseescalate
Output Contract
Return findings first, ordered by severity, and include:
verdictscopedraftrelated ADRspublic docsspecssrctestsissue / PR context
findings
Each finding should include:
typedecision-gapscope-conflictevidence-riskrollout-gapownership-escalation
severitysummarywhy it matterssuggested revisionevidencedraftrelated sources
Also include top-level:
open questionsresidual risks
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 70 lines · 66 tokens per session scan A 5e39ef81bf5e
adr-reviewer is a skill published in the GitHub repository harumiWeb/exstruct (204 stars, last pushed 26d ago), licensed BSD-3-Clause. It adds 66 tokens to every session and 614 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
visual-aspect-analyzer
Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and the change is not done until it reports score: 100. It drives a real browser over the page, auto-detects its relevant elements (no…
summarize-changes
Summarizes uncommitted changes and flags anything risky.
review-change
Review one change (a pull request, a diff, a branch) the way the factory's review stage does, grounded in the warranting library, and end with a plain-words sign-off sheet for someone who doesn't read code. Use when someone asks to review a change before it merges, asks whether they can sign a change off, or pastes a…
factory
Run a software change through the factory harness (spec, triage, locked tests, guarded build, deterministic gates, blind Claude + Codex review, warranty pack) and present the pack to the accountable person. Use when the user asks to build, gate, review or warrant a change with the factory, to resume a blocked factory…
weekly-review
How this household runs its Sunday weekly review.
review-agent
Perform a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.