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 vinsonconsulting/limner --skill iterate-on-assetgit clone --depth 1 https://github.com/vinsonconsulting/limnerWrote 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/vinsonconsulting/limner/iterate-on-asset)<a href="https://agentmods.dev/skills/vinsonconsulting/limner/iterate-on-asset"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/iterate-on-asset/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/vinsonconsulting/limner/iterate-on-asset"><img src="https://agentmods.dev/badge/skills/vinsonconsulting/limner/iterate-on-asset.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 | $0.00045 | $0.01155 |
| Opus 5 | $0.00023 | $0.00577 |
| Sonnet 5 | $0.00009 | $0.00231 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
iterate-on-asset 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterate on a prior asset
Limner is an independent third-party project built on Anthropic's CMA platform; it is not an Anthropic or Claude product.
Use this skill to build on a generation you made earlier: a variation, a restyle, or a finished export. Two facts shape the work. Every generation returns a fetchable capability URL, so a prior asset can feed straight back into a generator as image input. And Limner does not save generations for you, so recall depends on notes you record yourself. The reference at the end states the rules.
Procedure
- Record as you generate. After each generation worth keeping, save a note with limner_record (memory) or limner_record_project_note (a project): the asset URL, the prompt, the pipeline, and the key parameters. Nothing is saved automatically.
- Recall the prior asset. Search memory with limner_recall, or read a project with limner_get_project_context, then read the URL and parameters back out of the note.
- Decide the move: a variation or restyle, a small same-style change, or a finishing step.
- Vary or restyle. Pass the recalled URL as image input to a generator and describe the change, or re-run the same pipeline with the recalled prompt and tweaked parameters.
- Finish if that is the goal. Upscale, vectorize, or compose (crop, caption, stamp) the recalled asset instead of regenerating.
- Close the loop. Record the new asset the same way, noting it derives from the prior one.
Judgment
- Record enough to act cold. A note you cannot iterate from later is not worth writing: capture the URL, prompt, pipeline, and parameters.
- Pass the URL as image input when you want to keep the look and change details; re-run from the prompt when you want a fresh take in the same style.
- Reuse a Midjourney seed to hold a composition while you vary other knobs.
- Post-process instead of regenerating when the asset is right and only needs scale, format, or a finish. It is cheaper and keeps the pixels.
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.
- 12d ago First seen · 82 lines · 45 tokens per session scan A d09a220b6035
iterate-on-asset is a skill published in the GitHub repository vinsonconsulting/limner (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,155 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
supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
potpie-graph
Use when the task can read or write the project-memory graph through the potpie CLI: discover the contract with graph catalog, read named views with graph read, resolve entity identity with graph search-entities, create validated plans with graph propose, commit plans with graph commit --verify, inspect quality with…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.
aatmf-t04-memory-manipulation
AATMF T4 — Multi-Turn & Memory Manipulation. Persistent memory injection, conversation-state poisoning, cross-session contamination, ghost-context leak.