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 acligit 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/acli)<a href="https://agentmods.dev/skills/fmind/dot/acli"><img src="https://agentmods.dev/badge/skills/fmind/dot/acli/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/acli"><img src="https://agentmods.dev/badge/skills/fmind/dot/acli.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 | $0.00020 | $0.00890 |
| Opus 5.5 | $0.00008 | $0.00356 |
| Sonnet 5.5 | $0.00004 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
acli 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Atlassian CLI
Use acli for Jira and Confluence Cloud from the shell. Atlassian publishes no skill for acli itself, so this skill owns authentication, bounded reads, and the write boundary.
Workflow
-
Resolve the account: use
acli auth status,acli auth login, andacli auth switchfor OAuth accounts. API-token authentication is per service:acli jira authandacli confluence autheach providelogin,status, andswitch; pipe the token on stdin, never as an argument.acli jira auth login --site <site>.atlassian.net --email <email> --token < token.txt acli confluence auth login --site <site>.atlassian.net --email <email> --token < token.txt -
Bound every read: JQL with a limit and explicit fields, JSON for anything a tool parses.
acli jira workitem search --jql 'project = TEAM AND status != Done' --fields key,summary,status --limit 50 --json acli jira workitem view TEAM-123 --fields summary,status --json acli confluence page view --id <page-id> --body-format storage --json -
Expand content selectively: add
descriptionorcommentwhen the requested work needs them. Treat a search that reaches its--limitas partial: check the total with--count, then narrow the JQL or use--paginatebefore claiming completeness. -
Write with authority: reuse existing authority for the requested keys, fields, and effects; ask only when consequential scope is missing. Comments, assignments, and bulk operations must be included in that authority. Prefer
--generate-jsonthen--from-jsonfor reproducible creations, and pass multiline text through files (--description-file,comment create --body-file) instead of inline arguments.acli jira workitem create --project TEAM --type Task --summary "<summary>" --description-file description.txt --json acli jira workitem transition --key TEAM-123 --status "In Progress" acli jira workitem comment create --key TEAM-123 --body-file comment.txt
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 Changed 6a939037422f
- 14d ago Changed 2c001b1c85ec
- 15d ago Changed · +1 lines 873054e46981
- 23d ago Changed · +1 lines 42ccd31c0039
- 29d ago Changed 398ce72c1c55
- 1mo ago Changed · +1 lines · -28 tokens per session f0e1d3b8976d
- 1mo ago Changed · +1 lines d2710e322b68
- 1mo ago Changed d1e44a6c7cfd
- 1mo ago First seen · 52 lines · 48 tokens per session scan A b9189041e2cb
acli is a skill published in the GitHub repository fmind/dot (12 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 890 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 2026-09-03.
Other skills, from other repositories
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
product-loop
Discovery, specification, launch, and learning for a product in one loop. Build-or-stop calls, MVP wedges, demand tests, customer interviews, PRDs, requirements, user journeys, acceptance, positioning, onboarding, rollout, pricing, pivots.
project-backlog
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before GitHub mutation.
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…
podio-ticket-updates
Sync in-progress Podio Kanban tickets with progress from their linked GitHub repos — propose description updates and progress comments, apply after approval. Use when the user asks to update Podio tickets, sync ticket progress, or post status updates to the Kanban board.