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/fmind/dotfiles/project-backlognpx skills add fmind/dotfiles --skill project-backloggit clone --depth 1 https://github.com/fmind/dotfilesWhat 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 | $0.00025 | $0.01121 |
| Opus 5 | $0.00013 | $0.00561 |
| Sonnet 5 | $0.00005 | $0.00224 |
| Haiku 4.5 | $0.00003 | $0.00112 |
Grade A, and why
project-backlog 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 yesterday.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Backlog
Compose the repository-review skill with the repository's live issue taxonomy. Discovery and drafting are read-only by default; issue creation and native dependency mutation are a separate, explicitly authorized phase.
Local repository discovery requires git; live issue reads and authorized writes require gh.
Use the complete draft contract and exercise the failure boundaries in the behavioral evaluations.
Phase 1: Read-only discovery
- Confirm the local repository and read its instructions. Preserve staged, unstaged, and untracked work exactly as required by the repository-review skill.
- Resolve the candidate GitHub repository with
gh repo view --json nameWithOwner,url,visibility; show it to the user, but do not treat discovery as mutation authorization. - Run the cross-cutting repository review across source, tests, tooling, CI/CD, security, documentation, generated state, release state, and relevant authorized live behavior. Retain partial scans and unavailable services as evidence gaps.
- Fetch open and closed issues needed for duplicate analysis, including complete bodies, comments, labels, state, and native
blockedByandblockingrelationships. Search by the underlying problem and evidence, not title similarity alone. - Research current primary documentation or upstream source only where it can materially confirm a retained finding or implementation boundary. Record the publication or version context and distinguish sourced fact from inference.
- Classify each candidate as a verified finding or trend opportunity. A trend becomes an issue only when current project evidence proves fit and value; popularity, novelty, or a generic best practice is insufficient.
- Reject candidates that duplicate an existing issue, lack reproducible evidence, exceed the project's likely value, restore intentionally rejected scope, or add unjustified complexity.
- Draft every retained item with draft-contract.md. Explain why it is distinct from every close match and model dependencies as draft-to-draft or draft-to-existing-issue edges.
- Present the deduplication decisions, ordered drafts, and dependency graph for review. Stop here unless the user explicitly authorizes creation in the displayed repository.
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.
- yesterday First seen · 58 lines · 25 tokens per session scan A 53159fda850a
project-backlog is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 1,121 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
todoist-cli
Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the td CLI. Use when the user wants to view, create, update, complete, or organize Todoist items, or mentions tasks, inbox, today, upcoming, projects, labels, or filters.
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…
doctor
Diagnose vault and plugin health — checks broken links, orphan notes, stale memory/ files, inbox backlog, and plugin config validity. Use when the user asks to check vault health, notices something broken, or wants a system audit — 'run /doctor', 'check my vault', 'something seems off'. Do NOT use for: searching vault…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…