Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add liza-mas/liza --skill adr-backfillgit clone --depth 1 https://github.com/liza-mas/lizaWrote 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/liza-mas/liza/adr-backfill)<a href="https://agentmods.dev/skills/liza-mas/liza/adr-backfill"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/adr-backfill/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/liza-mas/liza/adr-backfill"><img src="https://agentmods.dev/badge/skills/liza-mas/liza/adr-backfill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00013 | $0.03894 |
| Opus 5 | $0.00006 | $0.01947 |
| Sonnet 5 | $0.00003 | $0.00779 |
| Haiku 4.5 | $0.00001 | $0.00389 |
Grade A, and why
adr-backfill 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 11d 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
Reconstruct Architecture Decision Records from a repository's git history and documentation. You're doing archaeology — finding the decisions buried in commits, specs, and docs, then surfacing them as ADRs.
An ADR is warranted when someone made a choice that shaped the system. Not every commit is a decision. Your job is to find the ones that were.
Process
-
Classify files — Distinguish architectural files (where decisions manifest) from supportive files (tests, utils). Persist this classification.
-
Identify candidate commits — Find commits that touch architectural files with structural changes (not just edits).
-
Cluster into decisions — Group related commits that represent a single decision being implemented.
-
Fill gaps — Pull in minor commits (typo fixes, forgotten files) that belong to a cluster but were filtered out.
-
For each cluster — Analyze intent, ask the user for context, generate the ADR.
-
Scan complementary sources — Check
specs/anddocs/for decisions not captured by commits. -
Enrich ADRs — Add cross-references, diagrams, and implementation notes from related documentation.
-
Order chronologically — Renumber ADRs to maintain chronological sequence.
-
Update ADR index — Keep
specs/architecture/ADR/README.mdin sync after any ADR is added, removed, or renumbered.
Maintain state in files so work isn't lost if the conversation ends.
1. File Classification
Consider all files - present and deleted. Deletion may reveal an architectural decision.
Architectural (decisions live here)
Tier 0 — Dependency manifests (highest signal)
requirements.txt,pyproject.toml,package.json,go.mod,Cargo.toml- Every addition/removal is a technology choice
Tier 1 — Infrastructure & deployment
Dockerfile,docker-compose*.yml, CI configs, terraform, k8s manifests- How the system runs and deploys
Tier 2 — Domain structure
- Core modules, domain boundaries, entry points, service definitions
- The shape of the system
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.
- 11d ago First seen · 472 lines · 13 tokens per session scan A d67dc935c0f2
adr-backfill is a skill published in the GitHub repository liza-mas/liza (384 stars, last pushed 2d ago), licensed Apache-2.0. It adds 13 tokens to every session and 3,894 once invoked, about $0.0001 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…