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 task-promptsgit 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/task-prompts)<a href="https://agentmods.dev/skills/fmind/dot/task-prompts"><img src="https://agentmods.dev/badge/skills/fmind/dot/task-prompts/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/task-prompts"><img src="https://agentmods.dev/badge/skills/fmind/dot/task-prompts.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 | $0.00014 | $0.00514 |
| Opus 5.5 | $0.00006 | $0.00206 |
| Sonnet 5.5 | $0.00003 | $0.00103 |
| Haiku 4.5 | $0.00001 | $0.00051 |
Grade A, and why
task-prompts 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 7d 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.
What it actually says
Task and Continuation Prompts
Prepare instructions the receiving agent can use without this conversation. system-prompts owns prompts embedded in applications; native resume or compaction is preferable when it already preserves the needed state.
Workflow
- Choose the mode: fresh task, or continuation of work already underway; resolve the requested outcome, latest corrections, scope, and acceptance criteria.
- Record continuation state: check
git status --short --branch, record completed proof, the exact stopping point, outstanding work, failed approaches, and reasons for material decisions. Before/clearor a harness switch, use handoff, which also copies the result to the clipboard. - Draft from prompt-template.md; omit empty sections and add ordered slices only when execution needs them.
- Write and check: resolve the root with
git rev-parse --show-toplevel; save.agents/prompts/<file>.md, defaulting to<YYYY-MM-DD>-<slug>.md, or~/.agents/prompts/outside a repository. Verify the receiver can act without hidden context, then report the path.
Gotchas
- Authority travels with the task: distinguish authorized actions from proposed work; writing the prompt does not grant additional permission.
- Keep history useful, not copied: preserve failures and proof gaps; cite code paths and lines instead of copying source or the shared persona.
- Keep the prompt inbox untracked: keep
.agents/prompts/gitignored unless the user wants it tracked; keep a small continuation short.
Documentation
- Companion skills: research-brief (decision evidence), implementation-plan (ordered slices), agent-project (host layout), handoff (save and copy before
/clear).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed · -3 tokens per session be05e684832a
- 9d ago Changed · -1 lines 4962e0ed06d7
- 11d ago Changed 2f7ef392c589
- 12d ago Changed · -1 tokens per session 967b28fe3f81
- 26d ago Changed dda17244cdc3
- 29d ago First seen · 34 lines · 18 tokens per session scan A 52b3504bd996
task-prompts is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 14 tokens to every session and 514 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 2026-09-17.
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.