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 freezingfunky/ashwin-skills --skill agent-designgit clone --depth 1 https://github.com/freezingfunky/ashwin-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/freezingfunky/ashwin-skills/agent-design)<a href="https://agentmods.dev/skills/freezingfunky/ashwin-skills/agent-design"><img src="https://agentmods.dev/badge/skills/freezingfunky/ashwin-skills/agent-design/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/freezingfunky/ashwin-skills/agent-design"><img src="https://agentmods.dev/badge/skills/freezingfunky/ashwin-skills/agent-design.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 | $0.00094 | $0.01964 |
| Opus 5.5 | $0.00038 | $0.00786 |
| Sonnet 5.5 | $0.00019 | $0.00393 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
agent-design 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 2mo 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent design — decision map, then four pillars
Most "I'm not good at building agents" is really "I build them by feel and can't predict whether the next one will be good." The fix is to name the method.
A working agent is four things, and a weak agent is usually missing one:
Task · Context · Memory · Eval.
But first: one agent = one outcome. If you can name two outcomes that succeed or fail independently, you have two agents — each gets its own design pass.
0. Decision map — singular outcome or split
Do this before filling the pillars. Completion criterion: either (a) one singular DONE/FAILED pair locked, or (b) an explicit split list, this session designs one, and parked agents are either fan-out-spawned after confirm or left for later re-entry.
Steps
- Draft the singular outcome in one sentence (what "this agent worked" means).
- List aspects that feel like separate focuses (intake, summarize, notify, …).
- Smell test each aspect: same DONE/FAILED as the draft outcome?
- Same → keep inside this agent.
- Independent success/fail → split into a separate agent name + its DONE.
- Emit one of:
- One agent — proceed to pillars below for that outcome.
- Multiple agents — print the full split table (name · DONE · FAILED). Pick one to design in this session (recommend the dependency-root). Park the rest. Then run §0b Fan-out before or while continuing pillars for the in-session agent.
- Fog vs size:
- One outcome, still foggy (open decisions) → stay in the decision map; resolve open questions one at a time until the outcome is sharp.
- One outcome, too big for one run → still one agent design; use handoff/memory across runs — do not invent a second agent unless the outcome splits.
0b. Fan-out (parked agents → parallel sessions)
Never spawn without an explicit user confirm. Silent fan-out is a failure mode.
After the split list is on screen, ask once:
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.
- 2mo ago First seen · 175 lines · 94 tokens per session scan A 45a9e82be40e
agent-design is a skill published in the GitHub repository freezingfunky/ashwin-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,964 once invoked, about $0.0004 per session on Opus 5.5. 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
oma-scholar
Search academic literature and generate, validate, or compare Knows paper sidecars. Use for claim/evidence analysis and literature synthesis.
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.