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 naimkatiman/continuous-improvement --skill loftgit clone --depth 1 https://github.com/naimkatiman/continuous-improvementWrote 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/naimkatiman/continuous-improvement/loft)<a href="https://agentmods.dev/skills/naimkatiman/continuous-improvement/loft"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/loft/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/naimkatiman/continuous-improvement/loft"><img src="https://agentmods.dev/badge/skills/naimkatiman/continuous-improvement/loft.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 | $0.00096 | $0.01211 |
| Opus 5 | $0.00048 | $0.00606 |
| Sonnet 5 | $0.00019 | $0.00242 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
loft 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 3d 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
100% identical to loft — 0 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loft
Cut no steel until the shape is fair. Shipwrights loft the hull's lines full-scale and fair them before a single plate is cut. Loft applies the same order to design questions: when words have run out — two plausible answers, neither falsifiable by talk — build a cheap runnable artifact, let the captain react to it, and fold that reaction into the decision.
The role contract. The crew builds the artifact; the captain's only job is to react — and that reaction is the decision. The artifact is an instrument for seeing, never a head start on the deliverable.
When to loft
- a design question stalls in prose: repeatedly rephrased, still not settleable ("how should the path page look", "does this state model feel right")
- a navigator map carries a
loftticket - a spec discussion reaches "we would have to see it first"
Do not loft when:
- the question is answerable from repo evidence or by asking the captain (that is interviewing, not lofting)
- the destination itself is unclear (that is fog —
/oh-my-claudecode:ask-navigator) - the answer already lives in an ADR (do not re-loft settled decisions)
- the "design question" is actually a bug (that is the debugger's jurisdiction)
Choose the fork
Pick by what the question is asking. A wrong fork wastes the whole artifact.
Logic fork — is the model right?
For questions about state, business rules, data shape, or algorithms ("does unlocking regress on a retake?", "does this reducer hold at the edges?"):
- Isolate the decision-bearing core — the state machine, reducer, schema, or algorithm — as a pure module: no DOM, no I/O, no framework. Written so that, once the shape is confirmed, it moves into the real codebase unchanged.
- Wrap it in a single clickable HTML shell: one button per scenario, the tricky edge cases walked through in order, full state visible after every click.
- On confirmation the module is ready to lift — it re-enters as real work through launch. During the loft itself
mainstays untouched and the shell stays behind on the branch.
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.
- 3d ago First seen · 71 lines · 0 tokens per session scan A 4d2bacc4e665
loft is a skill published in the GitHub repository naimkatiman/continuous-improvement (7 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 1,211 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to loft, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
html-ppt-zhangzara-blue-professional
OpenDesign's QBR for the executive committee: what moved, what stalled, and the resource reallocation ask. Built as a decision-grade corporate strategy deck for executive committee.
html-ppt-zhangzara-pink-script
A wedding-anniversary tribute photo essay — a decade in scenes, the turning points, and the quiet meaning of staying. Built as a decision-grade story deck for couple, family, friends.
html-ppt-zhangzara-retro-windows
An IT security-awareness training on spotting phishing — the tells, the drill, and what to do in the first 60 seconds. Built as a decision-grade professional training deck for all employees.
pricing-page
A standalone pricing page — header, plan tiers, feature comparison table, and an FAQ. Use when the brief asks for "pricing", "plans", "subscription tiers", or a "compare plans" page.
huashu-bento-insight
OpenDesign vs closed cloud design tools: a side-by-side displacement case on control, cost (BYOK), and lock-in. Built as a decision-grade B2B sales deck for evaluation committee.
huashu-keynote-black
OpenDesign's all-hands: the year in review, the three priorities, and what every team owns next quarter. Built as a decision-grade corporate strategy deck for whole company.