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 vijayjoshi24/ea-agent-skills --skill adr-writergit clone --depth 1 https://github.com/vijayjoshi24/ea-agent-skillsWrote 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/vijayjoshi24/ea-agent-skills/adr-writer)<a href="https://agentmods.dev/skills/vijayjoshi24/ea-agent-skills/adr-writer"><img src="https://agentmods.dev/badge/skills/vijayjoshi24/ea-agent-skills/adr-writer/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/vijayjoshi24/ea-agent-skills/adr-writer"><img src="https://agentmods.dev/badge/skills/vijayjoshi24/ea-agent-skills/adr-writer.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 | $0.00106 | $0.00858 |
| Opus 5 | $0.00053 | $0.00429 |
| Sonnet 5 | $0.00021 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
adr-writer 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Writer
Capture architectural decisions as durable, structured ADRs. A decision not documented is a decision that will be re-litigated — usually at the worst moment.
Step 1 — Extract the Decision Context
From the user's description, identify:
- The decision — what was chosen or what needs to be chosen
- The context — what forces, constraints, and requirements drove this
- The options — what alternatives were considered (ask if not provided)
- The deciders — who made or will make this call
- The consequences — what becomes easier, harder, or different as a result
If the user is still deliberating (hasn't decided yet), run the options comparison in Step 2 first, then write the ADR once they confirm a direction.
Step 2 — Options Comparison (when deciding)
If the user has multiple options to evaluate, produce a comparison table:
| Criterion | Option A | Option B | Option C |
|---|---|---|---|
| Fit for use case | |||
| Operational complexity | |||
| Team skill match | |||
| Cost | |||
| Vendor/lock-in risk | |||
| Time to implement | |||
| Verdict |
Score each cell: ✅ Strong / ⚠️ Acceptable / ❌ Weak
End with a clear recommendation and one-sentence rationale.
Step 3 — Write the ADR
Use this exact format. Do not skip sections.
# ADR-NNN: {Concise title — what was decided, not just the topic}
**Date:** {YYYY-MM-DD}
**Status:** Proposed | Accepted | Deprecated | Superseded by ADR-NNN
**Deciders:** {names or roles}
**Tags:** {technology | pattern | platform | integration | security}
## Context
{What situation, constraint, or requirement makes this decision necessary?
What would happen if we made no decision? 2–4 sentences max.}
## Decision
{Active voice: "We will adopt / use / implement / reject..."
State the decision unambiguously in 1–2 sentences.}
## Options considered
| Option | Summary | Key trade-off |
|--------|---------|---------------|
| {A} | | |
| {B} | | |
## Consequences
### Positive
- {What becomes easier, faster, or safer}
### Negative
- {What becomes harder, more constrained, or more expensive}
### Risks and mitigations
| Risk | Likelihood | Mitigation |
|------|-----------|------------|
## Related decisions
- Supersedes: —
- Related to: —
- Enables: —
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 · 122 lines · 106 tokens per session scan A fa841fd2b918
adr-writer is a skill published in the GitHub repository vijayjoshi24/ea-agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 106 tokens to every session and 858 once invoked, about $0.0005 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.
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…