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 mhenke/john-ousterhout-skills --skill aposdgit clone --depth 1 https://github.com/mhenke/john-ousterhout-skillsWrote 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/mhenke/john-ousterhout-skills/aposd)<a href="https://agentmods.dev/skills/mhenke/john-ousterhout-skills/aposd"><img src="https://agentmods.dev/badge/skills/mhenke/john-ousterhout-skills/aposd/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/mhenke/john-ousterhout-skills/aposd"><img src="https://agentmods.dev/badge/skills/mhenke/john-ousterhout-skills/aposd.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 | $0.00030 | $0.03761 |
| Opus 5 | $0.00015 | $0.01880 |
| Sonnet 5 | $0.00006 | $0.00752 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade A, and why
aposd 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.
How it starts
The opening of the file, as written. The whole thing — 375 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content source:
CLAUDE.mdis the single source of truth for the 15 behavioral rules — make changes to those there first, then copy here. Sections unique to this file (Setup, Quick Reference, Common Mistakes, Invocation Modes) are maintained here directly. See ADR-005 (Intentional Condensation). Examples inreferences/.
APOSD behavioral guidelines
Design-quality guardrails for every coding task. APOSD applies 15 principles from A Philosophy of Software Design (Ousterhout) — always-on behavioral guidance that pushes toward deeper modules, cleaner interfaces, and less error handling for callers. No explicit invocation needed for everyday coding.
Scope
In scope: Design analysis, modular decomposition, interface design, naming, error-handling strategy, abstraction layering, code review with a design lens.
Deliberately out of scope:
- Low-level debugging or performance profiling
- Framework-specific patterns (React, Django, etc.)
- CI/CD configuration, deployment, infrastructure
- Security auditing — see the dedicated security skills
Boundary with sibling skills: This skill provides design principles and behavioral guidance. The sibling skills below cover formal evaluation passes:
| Skill | Purpose | When to Use |
|---|---|---|
| aposd (this skill) | Always-on design principles during coding | Every task with design decisions |
| aposd-critique | Principles-based design evaluation | Deep design review, second opinion on complexity |
| aposd-audit | Severity-scored design audit | Before major refactoring, baseline current state |
When Not to Use
This skill is designed for non-trivial design decisions. Skip it for:
- Trivial one-line fixes (typo, variable rename, config change)
- Mechanical refactors with no design impact (rename a method, extract a constant)
- Exploratory code where the design is intentionally provisional
The tradeoff note at the top of Principles covers this: "For trivial tasks, use judgment."
What ships with it
9 files 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.
- references/examples.md 1.6 KB
- references/principles.md 17 KB
- references/routing.md 1.3 KB
- references/scoring.md 2.6 KB
- references/troubleshooting.md 1.9 KB
- templates/deep-module.py 1.2 KB runs code
- templates/error-suppressor.py 786 B runs code
- templates/manifest.json 580 B
- templates/manifest.toml 557 B
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 · 375 lines · 30 tokens per session scan A 8bb494e155ee
aposd is a skill published in the GitHub repository mhenke/john-ousterhout-skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 3,761 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
Cognitive Load Analyzer
Evaluate interface complexity by measuring information density, decision points, visual hierarchy, and task completion paths to reduce user cognitive burden.
software-code-review
Evaluate source code for correctness, quality, security, style conformance, and maintainability, producing a structured review report with findings and recommendations. Use when the user wants to review, critique, audit, evaluate, or inspect source code — checking for bugs, logic errors, unhandled error paths…
software-design-review
Critically review a software design specification and suggest concrete improvements. Use when the user wants to review, critique, audit, evaluate, or strengthen a design spec, technical specification, feature design, architecture proposal, or implementation plan. Focus on clarity, completeness, correctness…
systems-thinking
Analyzes complex business problems through systems thinking by mapping causal loops, identifying reinforcing and balancing feedback dynamics, and diagnosing system archetypes like Fixes That Fail, Shifting the Burden, and Limits to Growth. Use when quick fixes keep backfiring, growth plateaus unexpectedly, departments…
software-design-creation
Create software design specifications for new features or standalone software. Use when the user needs help turning a brief idea into a concrete design spec by eliciting missing requirements, clarifying scope, defining users and constraints, outlining architecture and interfaces, identifying risks and assumptions, and…
tldr-code
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.