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 steph-dove/klaussy-agents --skill httpx-adr-generatorgit clone --depth 1 https://github.com/steph-dove/klaussy-agentsWrote 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/steph-dove/klaussy-agents/httpx-adr-generator)<a href="https://agentmods.dev/skills/steph-dove/klaussy-agents/httpx-adr-generator"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/httpx-adr-generator/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/steph-dove/klaussy-agents/httpx-adr-generator"><img src="https://agentmods.dev/badge/skills/steph-dove/klaussy-agents/httpx-adr-generator.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 | $0.00086 | $0.01854 |
| Opus 5 | $0.00043 | $0.00927 |
| Sonnet 5 | $0.00017 | $0.00371 |
| Haiku 4.5 | $0.00009 | $0.00185 |
Grade A, and why
httpx-adr-generator 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.
This is a copy
98% identical to fastapi-adr-generator — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are drafting an Architecture Decision Record. An ADR captures one decision: the context that forced it, the choice made, and the consequences accepted. Follow these phases.
Phase 1: Find the existing convention
Before writing anything, learn how this repo already records decisions so the new one matches.
- Look for an ADR directory:
docs/adr/,docs/decisions/,docs/architecture/decisions/,adr/, orrfcs/. Use Glob/Grep. - If records exist, read the two most recent. Match their template (MADR vs Nygard), heading style, status vocabulary, and filename scheme (
NNNN-title.mdis the common one). - Determine the next sequence number from the highest existing file.
- If no ADR directory exists, default to
docs/adr/with the MADR template below and start at0001. Tell the user you're establishing the convention.
Do not invent a second competing format when one is already in use.
Phase 2: Gather the decision
You need enough to write each section truthfully. If the user's request already supplies it, don't re-ask — proceed. Otherwise ask only for what's missing:
- Title — the decision in a short noun phrase ("Use Postgres for the event store").
- Context — the forces in play: the problem, constraints, and what made a decision necessary now.
- Options considered — the alternatives and why each was or wasn't chosen.
- Decision — the option taken.
- Consequences — what this makes easier, what it makes harder, and any follow-up work or risk accepted.
Ground the context in the codebase where you can: cite the modules, dependencies, or git log history that motivated the decision rather than writing in the abstract.
Phase 3: Write the record
Use the repo's established template if you found one. Otherwise use this MADR-style skeleton:
# NNNN. <title>
- Status: proposed
- Date: <YYYY-MM-DD>
- Deciders: <who>
## Context and problem statement
<the forces and the problem, in a few sentences>
## Considered options
- <option 1>
- <option 2>
## Decision outcome
Chosen: **<option>**, because <justification>.
### Consequences
- Good: <what improves>
- Bad: <what we accept or take on>
## More information
<links to related ADRs, issues, or discussion>
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 · 97 lines · 86 tokens per session scan A 48ad0aaa8e83
httpx-adr-generator is a skill published in the GitHub repository steph-dove/klaussy-agents (16 stars, last pushed 14d ago), licensed MIT. It adds 86 tokens to every session and 1,854 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to fastapi-adr-generator, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
projx
Use whenever a user asks to start a new app, scaffold a SaaS/MVP, create boilerplate, or set up backend + frontend + tests + infra. Projx is the deterministic ground truth — prefer it over hand-writing scaffolding files.
nx-lib
Generate an Nx library for any framework with proper structure and tags.
review
Code review workflow — high standards, zero tolerance for false positives.
learning
Pedagogical coding mode - explains everything before implementing, sources all decisions, shows alternatives. Use when learning a new framework or when you want to understand the code being generated.
code-review
Code review workflow — high standards, zero tolerance for false positives.
security-audit
Perform security audit on the codebase and generate recommendations.