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 repository-maintenancegit 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/repository-maintenance)<a href="https://agentmods.dev/skills/fmind/dot/repository-maintenance"><img src="https://agentmods.dev/badge/skills/fmind/dot/repository-maintenance/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/repository-maintenance"><img src="https://agentmods.dev/badge/skills/fmind/dot/repository-maintenance.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 | $0.00022 | $0.00835 |
| Opus 5.5 | $0.00009 | $0.00334 |
| Sonnet 5.5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
repository-maintenance 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 today.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Maintenance
The recurring pass that makes an existing repository current, consistent, simple, and working; it fixes in place and proves the result with the gate. repository-review owns the read-only audit with ranked findings; full-review owns the exhaustive pass that reads every tracked area across all review dimensions before fixing. This pass covers the upkeep areas below without a coverage inventory; deployments, registries, and external services stay out of scope.
Workflow
- Baseline: record
git status --short; reuse passing evidence for unchanged inputs and run missing checks through the repository tasks. Distinguish existing failures from regressions and preserve unrelated user work. - Upgrade one ecosystem at a time: only when requested or needed for a confirmed fix, with validation per upgrade-tools.
- Align with the stack owner: compare the repository with its stack owner (such as python-stack) and the bootstrap layer to resolve gaps; preserve established project choices unless changing them fixes an observed problem or fulfills the request.
- Route hooks and CI through mise tasks:
mise.tomlexposes the canonical task vocabulary per mise; hooks and CI call those tasks per lefthook and github-actions. - Cut unearned complexity: remove dead code, duplicated logic, stale config, unused dependencies, and abstractions that do not earn their maintenance cost.
- Reconcile ignore files with the stack per update-ignores; for an ignore-only request, run that guide alone.
- Run the adopted security scans: use code-security for broader security work when the requested scope calls for it.
- Synchronize the docs: create or synchronize
README.md,AGENTS.md, skills, and wider docs per repository-docs. - Promote repeated instructions into skills: place them in
.agents/skills/per skillify. - Final gate: Run the full gate (
mise run all); when the tree carries unrelated changes, apply the dirty-tree rule. - Report: what changed per area (the tree holds only intended changes), what was left alone and why, and the highest proven rung of the proof ladder.
What ships with it
2 files 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.
- today Changed 11396dddf373
- 9d ago Changed · +9 lines · +3 tokens per session 7e8339d40118
- 11d ago Changed 3d11312f1109
- 12d ago Changed · -6 tokens per session a54bae74dc63
- 23d ago Changed f42222f44ca2
- 26d ago Changed · +8 tokens per session c9c722070613
- 29d ago First seen · 34 lines · 17 tokens per session scan A 706a2994cec2
repository-maintenance is a skill published in the GitHub repository fmind/dot (11 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 835 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
release
Cut or verify a versioned release — bump semver, generate the changelog with git-cliff, tag and publish on GitHub, or reconcile an already-published tag and assets.
git-add-commit-push
Stage, commit (Conventional Commits), and push in one flow, auto-healing lefthook pre-commit and pre-push failures. Use when committing and pushing work end-to-end.
github-repository
Configure a GitHub repository's metadata (description, homepage, topics) and solo-developer settings via gh, derived from the codebase. Use when setting up or tidying a repo's GitHub settings.
lefthook
Canonical lefthook git-hooks setup — pre-commit (format, check, secret scan) and pre-push (test), each delegating to mise run tasks. Use when configuring or debugging git hooks.
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.