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 DojoGenesis/mcp --skill adr-writergit clone --depth 1 https://github.com/DojoGenesis/mcpWrote 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/dojogenesis/mcp/adr-writer)<a href="https://agentmods.dev/skills/dojogenesis/mcp/adr-writer"><img src="https://agentmods.dev/badge/skills/dojogenesis/mcp/adr-writer.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 5.1 | $0.00048 | $0.02168 |
| Opus 5 | $0.00024 | $0.01084 |
| Sonnet 5 | $0.00010 | $0.00434 |
| Haiku 4.5 | $0.00005 | $0.00217 |
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 6d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Writer Skill
I. Philosophy
An Architecture Decision Record is the project's institutional memory. Every significant technical choice that lives only in someone's head is a future incident — a re-fight, a regression, or a confused new contributor asking why things work the way they do.
ADRs are not bureaucracy. They are the minimum viable documentation that keeps a fast-moving project from looping back on itself. A good ADR takes fifteen minutes to write and saves three hours of re-derivation six months later.
The crafter does not write ADRs for every change — only for decisions that:
- Are hard to reverse
- Affect multiple components or repos
- Were made between competing legitimate alternatives
- Will confuse someone who wasn't in the room
II. When to Use
- When a significant architectural choice is being made or was just made
- When two or more teams or components need to align on an approach
- When a previous decision is being revisited and the reason for the change should be recorded
- When a new contributor asks "why do we do X this way?" and the answer is not in the code
Do not write an ADR for trivial implementation choices, naming conventions, or decisions with only one viable option.
III. Workflow
Step 1: GATHER
Read the decision context before writing anything.
- Identify what is being decided and why it matters now. What forces are at play — performance, maintainability, velocity, contract compatibility, cost?
- Identify which repos, contracts, and interfaces are affected. Run
grepandglobsearches if needed — do not assume. - Identify who made or is making the decision. Note any external constraints (regulatory, contractual, hard deadlines) that eliminate certain routes.
- Check whether a prior ADR covers related ground. Search the
decisions/directory for existing ADR numbers and topics.
Step 2: SCOUT
Generate 3-5 routes before selecting one.
For each route:
- Description: What does this approach actually do?
- Risk: What can go wrong? What is the blast radius if it fails?
- Time: Rough estimate to implement
- Key tradeoff: What does this route give up to get its benefits?
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.
- 6d ago First seen · 201 lines · 48 tokens per session scan A 74974984ef66
adr-writer is a skill published in the GitHub repository DojoGenesis/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 2,168 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
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
redux-to-swr
Migrate React components from Redux + Saga to SWR hooks. Use when converting data fetching from Redux store (reducers, sagas, selectors, connect HOC) to SWR-based hooks in CockroachDB DB Console or cluster-ui.
mma-investigator
Expert system for investigating MMA (Multi-Metric Allocator) behavior on CockroachDB clusters. Helps oncall engineers diagnose load imbalances, understand rebalancing decisions, and identify why MMA did or didn't act.
migrate-state-management
Migrate Redux or React Context to the correct state option (React Query for server state, nuqs for URL/shareable state, Zustand for global client state). Use when refactoring away from Redux/Context, moving state to the right store, or when the user asks to migrate state management.
build-run
Build and run the project locally to reproduce compile/runtime issues in a safe, non-production way.
code-formatter
Apply repository-standard formatting to minimize diff noise and meet linter expectations.