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 zstevovich/claude-apd --skill apd-profilegit clone --depth 1 https://github.com/zstevovich/claude-apdWrote 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/zstevovich/claude-apd/apd-profile)<a href="https://agentmods.dev/skills/zstevovich/claude-apd/apd-profile"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-profile/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/zstevovich/claude-apd/apd-profile"><img src="https://agentmods.dev/badge/skills/zstevovich/claude-apd/apd-profile.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 | $0.00126 | $0.01308 |
| Opus 5 | $0.00063 | $0.00654 |
| Sonnet 5 | $0.00025 | $0.00262 |
| Haiku 4.5 | $0.00013 | $0.00131 |
Grade A, and why
apd-profile 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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APD Model Profile
Economy vs quality dial for pipeline agents. A profile maps role classes to a
(model, effort) pair: default (builders — context-heavy, carry the tier) and
adversarial (positional value — fresh context matters more than model tier,
so it may sit one tier below builders, never meaningfully above them).
Profiles are data, not code: defaults ship in the plugin
(templates/model-profiles.conf); a project may override the whole table via
.apd/model-profiles.conf. CC-only — Codex .toml agents are not touched.
When to use
- User asks to change agent models, make the pipeline cheaper or stronger, or names a profile (burn / cruise / eco).
- Before a launch-critical feature → suggest
burn. - Before a batch of small pre-scoped fixes / Lean tasks → suggest
eco.
When to skip
- Mid-pipeline (active spec-card) — the script refuses; finish or reset first.
- User wants a one-off model change for a single agent — that is a manual
frontmatter edit, not a profile (but warn that
apd profile statuswill flag it as drift afterwards).
Steps
-
Show current state:
bash .claude/bin/apd profile status -
Show available profiles and what each maps to:
bash .claude/bin/apd profile list -
Ask the user which profile to apply (AskUserQuestion with the profiles as options, current one marked). Briefly state the trade-off:
burn= maximum quality / maximum cost,cruise= strong daily default,eco= cheapest builders, for small well-scoped work.Supervision is topology, not a price tier (v7.0). Every profile carries a
supervisorrow, so every Full-mode run adds a frontier pass over the final diff before the verifier — on burn, cruise and eco alike. Say this at the decision point so the extra frontier dispatch is not a surprise, and do NOT present a cheaper profile as "the one without supervision": while that was true (v6.30, eco only) the profiles were different pipelines rather than one pipeline at three prices, and their telemetry was not comparable.
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.
- 10d ago First seen · 107 lines · 126 tokens per session scan A 3c7ee6dd09cc
apd-profile is a skill published in the GitHub repository zstevovich/claude-apd (5 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 1,308 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…