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 agentmods add skills/davidcpage/skill-issues/adrnpx skills add davidcpage/skill-issues --skill adrgit clone --depth 1 https://github.com/davidcpage/skill-issuesWhat 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 | $0.00031 | $0.00920 |
| Opus 5 | $0.00015 | $0.00460 |
| Sonnet 5 | $0.00006 | $0.00184 |
| Haiku 4.5 | $0.00003 | $0.00092 |
Grade A, and why
adr 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 yesterday.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Skill (Architecture Decision Records)
Lightweight decision records for capturing significant technical decisions with their context and reasoning.
Portable: Copy this skill directory to any repo. Configure location and format in CLAUDE.md.
First-Time Setup
On first use in a repo, confirm with the user:
-
Storage location - Default:
decisions/- Alternatives:
docs/adr/,docs/decisions/
- Alternatives:
-
File naming - Default:
NNN-short-name.md(e.g.,001-auth-approach.md) -
Additional frontmatter - Some repos require specific frontmatter (tags, authors, etc.)
Once confirmed, document the choices in CLAUDE.md under a "Design Decisions" or "ADRs" section.
When to Create an ADR
Create a decision record when:
- Multiple valid approaches exist with meaningful trade-offs
- Cross-cutting concerns affect multiple parts of the codebase
- The decision needs future reference (why did we choose X?)
- Stakeholder alignment is needed before implementation
Don't create ADRs for:
- Obvious implementation choices
- Decisions that won't matter in a month
- Pure style/formatting preferences
Rule of thumb: If you'd want to explain "why we did it this way" to a future contributor, write an ADR.
Lifecycle
Draft → Accepted → [Superseded by NNN]
- Draft: Under discussion, content may change
- Accepted: Decision made, document is stable (don't edit substance)
- Superseded: Replaced by a newer ADR (link to it)
No "Rejected" status - if you decide against something, either don't write an ADR or mark it Accepted with the decision being "we won't do X because..."
Recommended Structure
# ADR NNN: Title
**Status:** Draft | Accepted | Superseded by NNN
**Date:** YYYY-MM-DD
## Context
What situation or problem prompted this decision? Include relevant constraints.
## Decision
What was decided? Be specific and concrete.
## Consequences
What are the implications? Include both positive and negative.
## Alternatives Considered
What other options were evaluated? Why were they rejected?
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.
- yesterday First seen · 124 lines · 31 tokens per session scan A 11e8647fed00
adr is a skill published in the GitHub repository davidcpage/skill-issues (2 stars, last pushed 7mo ago), licensed MIT. It adds 31 tokens to every session and 920 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…