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/cpliakas/claude-code-engineering-leaders/write-adrnpx skills add cpliakas/claude-code-engineering-leaders --skill write-adrgit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWrote 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/cpliakas/claude-code-engineering-leaders/write-adr)<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/write-adr"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/write-adr.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.01085 |
| Opus 5 | $0.00023 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
write-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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write ADR
Produce a complete ADR document in MADR format for the decision described in
$ARGUMENTS.
Step 1 — Check for Decision Description
If $ARGUMENTS is empty, ask the user to describe the decision before
proceeding. Do not continue until a decision description is provided.
Step 2 — Determine Next ADR Number
Check the Chief Architect's project memory
(.claude/agent-memory/engineering-leaders-chief-architect/MEMORY.md) for a
configured ADR directory path.
If a directory is configured:
- Read the index file (typically
README.md) in that directory - Scan the ADR Index table for the highest existing number (e.g.,
0011) - Set
NEXTto that number plus one, zero-padded to 4 digits (e.g.,0012)
If no directory is configured:
- Generate the ADR document as output only (do not write to disk)
- Use
0001as the ADR number - Note in the output that the Chief Architect's memory can be configured with
an
adr_directorypath to enable automatic filing and sequential numbering
Step 3 — Gather Context
Before filling in the template, read relevant project context:
- CLAUDE.md for architecture conventions and domain language
- Existing ADRs in the configured directory (if available) for precedent and consistency
- Chief Architect's project memory for related decisions and architectural trajectory
- Any files, schemas, or code referenced in the decision description
Step 4 — Produce the ADR
Use this MADR template:
---
status: proposed
date: YYYY-MM-DD
deciders: [who was involved in this decision]
---
# ADR-NNNN: [Short title of solved problem and solution]
## Context and Problem Statement
[What situation or problem forced this decision? What constraints, requirements,
or competing concerns existed? Keep to 2-4 sentences. May be phrased as a
question.]
## Decision Drivers
- [Driver 1 — e.g., cost constraint, latency requirement, team expertise]
- [Driver 2]
## Considered Options
- [Option 1]
- [Option 2]
- [Option 3]
## Decision Outcome
Chosen option: "[Option N]", because [justification — reference decision drivers].
### Consequences
- Good, because [positive consequence]
- Good, because [positive consequence]
- Bad, because [negative consequence or trade-off]
- Bad, because [negative consequence or trade-off]
## Pros and Cons of the Options
### [Option 1]
- Good, because [argument]
- Neutral, because [argument]
- Bad, because [argument]
### [Option 2]
- Good, because [argument]
- Bad, because [argument]
### [Option 3]
- Good, because [argument]
- Bad, because [argument]
## More Information
[Additional context, links to related ADRs, evidence gathered during
evaluation, or notes on when this decision should be revisited. Omit this
section if genuinely not applicable.]
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.
- 5d ago First seen · 154 lines · 46 tokens per session scan A 53fb9f1ec1fb
write-adr is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 1,085 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.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
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…