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 fmind/dot --skill trimgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/trim)<a href="https://agentmods.dev/skills/fmind/dot/trim"><img src="https://agentmods.dev/badge/skills/fmind/dot/trim/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/fmind/dot/trim"><img src="https://agentmods.dev/badge/skills/fmind/dot/trim.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 | $0.00018 | $0.00938 |
| Opus 5.5 | $0.00007 | $0.00375 |
| Sonnet 5.5 | $0.00004 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
trim 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trim
Treat /trim <path> or "too verbose", "too complex", "simplify this" as a request to remove words, lines, and settings that carry nothing, while every fact, behavior, and the author's voice survive. Trimming is not summarizing: when the text is the deliverable (an article, a talk) and the user did not ask for a length, tighten sentences but keep its substance and length class. Arguments can set a target (to 300 words, -40%) or a scope. For code, repository-maintenance owns dead code and abstractions; apply these rules only with tests proving behavior.
Workflow
-
Measure: record lines, words, and estimated tokens (characters / 4) before editing; for skill catalogs and instruction files also run
dot agent context --project . --details(add--source .inside the fmind/dot checkout).wc -lwm <path> -
Map what must survive: list each claim, rule, number, command, flag, link, warning, and authority boundary. For configuration, capture the effective result so the trim can prove it changed nothing:
mise cfgandmise settings,dprint resolved-config,ruff check --show-settings <file>,docker compose config,chezmoi cat <target>, oryq -o jsonfor plain data. -
Cut, in this order:
- Duplication: the same rule stated twice; keep it at its owner and link from elsewhere.
- Restated defaults: settings equal to the installed tool's default, after verifying that default in its current docs or
--help(defaults change between versions). - Filler: introductions, hedges, recaps, "note that", tool narration, history ("previously…"), and generic tutorials the reader's tools already know.
- Dead entries: options for tools, paths, or features that no longer exist (prove absence with
rgorfd). - Verbose constructions: lists that can be one sentence, sentences that can be a clause, examples that only repeat the rule.
-
Never cut: facts with their evidence, numbers and dates, exact commands and flags, non-obvious gotchas with their reason, security and authority boundaries, links and citations, required structure (frontmatter, anchored headings, generated-index markers), the documentation URL comment at the top of a configuration, comments explaining a non-default choice, and anything the user asked to keep. Preserve the author's voice and stance; do not rewrite into a different style.
-
Prove equivalence: re-capture the effective configuration and diff it (it must be identical); re-run affected checks and tests; for prose, walk the survival list and confirm each item is still present or deliberately dropped with a reason. Run the repository's formatter and link checks for edited files.
-
Report: before/after lines, words, and tokens with the percentage, the categories removed, and any candidate cut you kept because it looked load-bearing. Ask before removing anything ambiguous instead of guessing.
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 Changed 52c9a9e84c3d
- 11d ago Changed 6c56add1fece
- 12d ago First seen · 45 lines · 18 tokens per session scan A 400d4dd02158
trim is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 938 once invoked, about $0.0001 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 2026-10-05.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
hugo
Canonical Hugo static-site stack with the Hextra docs theme — Hugo Modules, mise tasks, dprint, lefthook, and GitHub Pages deploy. Use for documentation sites, project docs, and static websites.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.