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 agentmods add skills/dosatos/minimise/loopnpx skills add dosatos/minimise --skill loopgit clone --depth 1 https://github.com/dosatos/minimiseWhat 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 | $0.00033 | $0.01212 |
| Opus 5 | $0.00016 | $0.00606 |
| Sonnet 5 | $0.00007 | $0.00242 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
loop 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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refining an artifact with a minimise loop
Loop vs job
A job runs a fixed task list once — you already know the steps. A loop repeats
plan → implement → evaluate against one artifact until the planner decides the goal is met (or
max_iterations is hit), with each iteration's critique feeding forward into the next plan.
If the tasks are already known and finite, this is the wrong command — that is /minimise:job.
Prerequisite
If mini --help fails, tell the user to run /minimise:setup and stop.
PROPOSE — nothing runs until the user says yes
The user asked for a loop, but the goal and the rubric are what actually decide when it stops,
and those are theirs to approve. Never author a spec or run mini loop new before they agree.
Put in front of them:
- The goal — one sentence, and it must contain the stopping condition. "Improve the README" never terminates; "improve the README until a first-time reader can set up, use, and test the project without asking a question" does. The planner reads this to decide when to stop.
- The evaluation dimensions — 2–4 named dimensions with a rubric each. These are what the loop scores itself on every iteration, so they are the actual definition of "good enough"; get them right with the user, not alone.
max_iterations— the ceiling on cost. Suggest at least 5 unless the work argues otherwise. The built-in planner prompt already treats a failing evaluate dimension as a default reason tocontinue(it only stops early if its summary states why the failure is acceptable) — a low ceiling defeats that by cutting the loop off before it can actually converge.evaluate.max_concurrent— suggest at least 8 so dimensions fan out fully in one round instead of queuing behind a low cap; only lower it if the dimension count is small or the work argues for staggering.- The ask — "Want me to run this as a mini loop, or keep iterating here?"
If the user says no, iterate inline and drop it.
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.
- 2d ago First seen · 97 lines · 33 tokens per session scan A 81903857a5b7
loop is a skill published in the GitHub repository dosatos/minimise (11 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 1,212 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.