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/dot/project-backlognpx skills add fmind/dot --skill project-backloggit 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/project-backlog)<a href="https://agentmods.dev/skills/fmind/dot/project-backlog"><img src="https://agentmods.dev/badge/skills/fmind/dot/project-backlog.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01080 |
| Opus 5 | $0.00017 | $0.00540 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Backlog
Turn repository-review findings into deduplicated, ordered issue drafts; discovery and drafting are read-only, and github-issues owns the authorized creation of each issue.
Workflow
- Confirm the target: Read the local repository and its instructions with
git, then resolve the candidate withgh repo view --json nameWithOwner,visibility; show it to the user without treating discovery as mutation authorization. - Review: Run the cross-cutting repository review; keep partial scans and unavailable services as evidence gaps.
- Read existing issues: Fetch the open and closed issues needed for duplicate analysis with complete bodies, comments, labels, state, and native
blockedByandblockingrelationships; search by the underlying problem and evidence, not title similarity. - Research sparingly: Consult primary documentation or upstream source only where it materially confirms a retained finding; record the version context and separate sourced fact from inference.
- Classify: Mark each candidate a verified finding or a trend opportunity; a trend becomes an issue only when current project evidence proves fit and value.
- Reject: Drop candidates that duplicate an existing issue, lack reproducible evidence, exceed the project's likely value, restore rejected scope, or add unjustified complexity.
- Draft: Write every retained item with the draft contract; explain why it is distinct from each close match and model dependencies as draft-to-draft or draft-to-issue edges.
- Stop at the gate: Present deduplication decisions, ordered drafts, and the dependency graph; proceed only when the user explicitly authorizes creation in the confirmed repository, which is the only mutation target.
- Create issues: Refresh visibility, labels, matching issues, and native dependencies immediately before writing and stop if drafts went stale; create each issue in draft order through github-issues and record draft ID, issue number, node ID, and URL after each success.
- Add edges: Only after every node exists, read current relationships and add the missing ones with the
addBlockedBymutation from the draft contract; never encode a dependency only in prose. - Verify: Read back every body, label set, and
blockedByandblockingrelationship from GitHub before claiming completion. - Report: Return these sections in order.
- Review evidence: highest proven rung of the proof ladder and material gaps.
- Deduplication: candidate-to-existing-issue decisions and distinctness rationale.
- Draft backlog: ordered drafts with routing and dependency edges.
- Authorization gate: exact repository and mutations awaiting approval, or the authorization already received.
- Mutation receipt: only after authorized writes; created issues, labels, verified native edges, and any partial state.
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.
- yesterday First seen · 49 lines · 35 tokens per session scan A 47be6d256927
project-backlog is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 1,080 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
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.
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.
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
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.
mise
Configure pinned mise tools and canonical install, format, check, test, build, and watch tasks shared by hooks and CI.