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 oborchers/fractional-cto --skill one-pattern-one-waygit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/one-pattern-one-way)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/one-pattern-one-way"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/one-pattern-one-way/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/oborchers/fractional-cto/one-pattern-one-way"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/one-pattern-one-way.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 | $0.00075 | $0.02999 |
| Opus 5.5 | $0.00030 | $0.01200 |
| Sonnet 5.5 | $0.00015 | $0.00600 |
| Haiku 4.5 | $0.00007 | $0.00300 |
Grade B, and why
one-pattern-one-way scanned grade B with 2 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
const resp = await fetch("https://api.example.com/payments", { // pattern 2 method: "POST", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const user = await axios.get("https://api.example.com/users/123"); How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One Problem, One Pattern, One Way
For each category of problem in a codebase, there is one pattern. One. Not "usually" one. Not "preferably" one. Not "one, except when it is more convenient to do something else." ONE.
Configuration loading? One way. Error handling? One way. Data validation? One way. HTTP requests? One way. Logging? One way. String constants? One way. The moment a second approach appears, you have two problems: the original problem and the problem of not knowing which solution to use. By the third approach, the codebase is a museum of abandoned conventions.
This is the most violated principle in software engineering. Not because developers do not understand it, but because every individual shortcut feels harmless. "It is just one place." "This module is different." "I will refactor it later." None of these excuses survive contact with a team.
The Categories
Every codebase faces the same categories of cross-cutting problems. For each one, pick a pattern and enforce it everywhere. The specific pattern matters less than the fact that there is exactly one.
Configuration
One settings pattern. Everywhere.
Python: Pydantic BaseSettings with .env file loading.
TypeScript: Zod schema validating process.env.
Go: Struct with envconfig tags.
Pick one. If the project uses Pydantic BaseSettings, then every module that needs a config value gets it from that settings object. No os.getenv() calls scattered in business logic. No dotenv.load() in random files. No config.yaml alongside the .env. One source of truth, one loading mechanism, one validation step.
GOOD:
from pydantic_settings import BaseSettings
class Settings(BaseSettings):
database_url: str
redis_url: str
stripe_api_key: str
max_retry_attempts: int = 3
model_config = {"env_file": ".env"}
settings = Settings()
BAD -- three config patterns in one project:
# settings.py -- Pydantic (pattern 1)
class Settings(BaseSettings):
database_url: str
# worker.py -- raw os.getenv (pattern 2)
REDIS_URL = os.getenv("REDIS_URL", "redis://localhost")
# billing.py -- dotenv + os.environ (pattern 3)
load_dotenv()
STRIPE_KEY = os.environ["STRIPE_API_KEY"]
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 343 lines · 75 tokens per session scan B 3820dffc4e8e
one-pattern-one-way is a skill published in the GitHub repository oborchers/fractional-cto (32 stars, last pushed 5d ago), licensed MIT. It adds 75 tokens to every session and 2,999 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…