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 2389-research/simmer --skill simmer-generatorgit clone --depth 1 https://github.com/2389-research/simmerWrote 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/2389-research/simmer/simmer-generator)<a href="https://agentmods.dev/skills/2389-research/simmer/simmer-generator"><img src="https://agentmods.dev/badge/skills/2389-research/simmer/simmer-generator/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/2389-research/simmer/simmer-generator"><img src="https://agentmods.dev/badge/skills/2389-research/simmer/simmer-generator.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 | $0.00051 | $0.01705 |
| Opus 5 | $0.00026 | $0.00852 |
| Sonnet 5 | $0.00010 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00170 |
Grade A, and why
simmer-generator 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simmer Generator
Produce an improved version of the artifact. This is targeted improvement based on the judge's ASI from the previous round — not a rewrite from scratch.
Context You Receive
- Current candidate: the full artifact text (single-file) or workspace path (workspace)
- Criteria rubric: what "better" means (2-3 criteria with descriptions)
- ASI: the highest-leverage direction to pursue (from previous judge round)
- Iteration number: which round this is
- Artifact type: single-file or workspace
- Background (optional): constraints, available resources, domain knowledge
- Panel deliberation summary (optional, if judge board enabled): what the judge panel concluded last round — WORKING elements to preserve, NOT WORKING approaches to avoid, DIRECTION for this iteration. Use this for execution context — if the panel said "lookup tables work well," use that to inform how you format your changes. Do NOT use it to decide what to change — that's the ASI's job.
You do NOT receive score history or previous candidates. This is intentional — work from the ASI, not from scores. Trust the ASI — the judge board has investigated the problem, deliberated, and proposed this direction based on evidence. Execute it skillfully.
What To Do
Seedless Iteration 1
If ASI says "First iteration — generate initial candidate":
- You are creating the seed artifact from a description
- Read the criteria carefully — they define what good looks like
- Produce a solid first draft that addresses all criteria
- Don't try to be perfect — the loop will refine it
Single-File Mode
- Read the ASI carefully. The judge identified the single highest-leverage fix. Address that specifically.
- Do not try to fix everything at once. Focused improvement compounds better than scattered edits. Address the ASI. If you notice other small improvements that don't conflict, fine — but the ASI is your primary target.
- Preserve what works. Don't regress on aspects that aren't mentioned in the ASI. If the ASI says "the CTA is too high-friction," don't rewrite the opening paragraph.
- Respect the artifact's natural scope. Growth is fine when the criteria demand it (an API spec needs error responses the seed didn't have). But for tightly scoped artifacts (tweets, taglines, email subject lines), don't expand beyond the format — improve within the constraints.
- Produce the full improved artifact. Not a diff, not instructions — the complete text. Write it to the file path specified by the orchestrator.
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.
- 9d ago First seen · 113 lines · 51 tokens per session scan A e88c65fbad70
simmer-generator is a skill published in the GitHub repository 2389-research/simmer (14 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,705 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
sillytavern-iterator
A writing workflow that takes work through drafting, review, revision, polishing, and finalising. It also uses checks such as reading error signals, searching for answers, and testing assumptions.
kaizen
Kaizen (改善): every process has waste; eliminate it incrementally.
dag-feedback-synthesizer
Synthesizes actionable feedback from validation results, confidence scores, and iteration triggers. Creates structured improvement guidance for re-execution. Activate on 'synthesize feedback', 'improvement suggestions', 'actionable feedback', 'iteration guidance', 'feedback generation'. NOT for iteration detection…
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
state-trees
Create, inspect, and edit StateTree assets — states, tasks, transitions, conditions, considerations, and property bindings for AI behavior and game logic (StateTreeService). Use when the user asks to build a StateTree, add states/tasks/transitions, bind task properties, set up Utility AI considerations, or wire…