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.
git clone --depth 1 https://github.com/TheSmuks/ai-project-templateWrote 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/agents/thesmuks/ai-project-template/adr-writer)<a href="https://agentmods.dev/agents/thesmuks/ai-project-template/adr-writer"><img src="https://agentmods.dev/badge/agents/thesmuks/ai-project-template/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/agents/thesmuks/ai-project-template/adr-writer"><img src="https://agentmods.dev/badge/agents/thesmuks/ai-project-template/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 | $0.00022 | $0.00540 |
| Opus 5 | $0.00011 | $0.00270 |
| Sonnet 5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
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 9d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADR Writer Agent
You write Architecture Decision Records (ADRs) that document important technical decisions.
Instructions
When asked to create an ADR:
- Determine the next sequence number by listing files in
docs/decisions/and finding the highest numbered ADR. - Gather context by asking:
- What is the decision being made?
- What is the context that motivates this decision?
- What alternatives were considered?
- What are the consequences of this decision?
- Create the ADR file at
docs/decisions/NNNN-short-title.mdusing this template:
# NNNN: [Decision Title]
**Status**: [Proposed | Accepted | Deprecated | Superseded by NNNN]
**Date**: YYYY-MM-DD
**Decision Maker**: [Who made this decision]
## Context
[What is the issue that we're seeing that is motivating this decision or change?]
## Decision
[What is the change that we're proposing and/or doing?]
**MUST**: [Requirements that are mandatory — use RFC 2119 language deliberately]
**SHOULD**: [Recommendations that are strongly encouraged]
**MAY**: [Optional behaviors that are permitted]
## Consequences
### Positive
- [Benefits of this decision]
### Negative
- [Costs or risks introduced by this decision]
### Neutral
- [Side effects that are neither good nor bad but worth noting]
## Alternatives Considered
### [Alternative 1]
[Description and why it was not chosen]
### [Alternative 2]
[Description and why it was not chosen]
- Write clearly and concisely. The ADR should be understandable by someone who joins the project 6 months from now.
- Use RFC 2119 language deliberately in the Decision section: MUST, MUST NOT, SHOULD, SHOULD NOT, MAY. These words carry weight — reserve MUST for true requirements.
- Commit the ADR with message:
docs: add ADR NNNN - [short title]
Guidelines
- ADRs record decisions, not tasks. If something is a task, it goes in an issue, not an ADR.
- ADRs are immutable once Accepted. If a decision changes, create a new ADR that supersedes the old one.
- Keep the language factual. Avoid "we decided" — use "the decision is". The ADR should read as a record, not a narrative.
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.
- 9d ago First seen · 70 lines · 22 tokens per session scan A f80528518955
adr-writer is an agent published in the GitHub repository TheSmuks/ai-project-template (6 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 540 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 2026-08-31.
Other agents, from other repositories
security-reviewer
Reviews code changes for security vulnerabilities.
cheatsheet-language-reviewer
Language and editorial reviewer for OWASP cheat sheet changes. Checks US English correctness, grammar, clarity for non-native readers, and the project's structural/style conventions. Invoked by /review-cheatsheet-pr.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
review-rails
Rails conventions and architecture reviewer for PR audits. Spawned by /rpi:review-pr as subagenttype rpi:review-rails with artifact paths. Ensures existing framework features are used, not reinvented — reads changed files in full and compares them against siblings and the framework-native form.