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 umputun/agterm --skill backlog-pickergit clone --depth 1 https://github.com/umputun/agtermWrote 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/umputun/agterm/backlog-picker)<a href="https://agentmods.dev/skills/umputun/agterm/backlog-picker"><img src="https://agentmods.dev/badge/skills/umputun/agterm/backlog-picker/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/umputun/agterm/backlog-picker"><img src="https://agentmods.dev/badge/skills/umputun/agterm/backlog-picker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00095 | $0.02024 |
| Opus 5.5 | $0.00038 | $0.00810 |
| Sonnet 5.5 | $0.00019 | $0.00405 |
| Haiku 4.5 | $0.00010 | $0.00202 |
Grade A, and why
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 1mo 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog
docs/backlog/ at a repo root holds work that is real but not being done now: a defect a change did not
introduce, drift with no user-visible symptom, a fix whose blast radius exceeded its value, an idea worth
keeping. One file per item. It is the maintainer's own list — it never gates anything and never reaches a
contributor.
Item format
docs/backlog/<slug>.md. The slug names the defect, not the file it lives in
(reopen-fallback-ignores-frontmost.md), so it can be cited from a commit and dedupe is a filename check.
---
worth: later
where: internal/store/reopen.go:537
added: 2026-08-05
---
# reopen fallback ignores the last-frontmost window
`reopen`'s fallback ignores which window was last frontmost once `frontmost` is nil, so a multi-window
user's last-window capture replays only when the exited window happened to be `windows.first`. Surfaced
reviewing PR #370; the fix touches restore ordering, which is why it was deferred rather than done inline.
Three frontmatter fields, written once and rewritten only when a later sighting of the same item sharpens it, which is the one case Appending below allows:
worth: yes | no | later— the honest triage call.nois a valid answer: a real item not worth the edit still belongs here, because writing it down is what stops it being rediscovered every review.where: path:line— omit when the item is not anchored to one place. Its path narrows the dedupe search alongside the slug and the line is a navigation hint that moves. Compare paths only when both items havewhere; two items missing it are not thereby the same item.added: YYYY-MM-DD— never updated, so it reads as age. A year-old item is itself information. Zero-pad it: a reader sorting on this field has nothing to fall back on when the value is not an ISO date.
The H1 is the title. The body below it is free — repro, what was tried, the review that surfaced it, links, a snippet. No required sections: a two-line item stays two lines, a gnarly one gets a page.
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.
- 1mo ago First seen · 141 lines · 95 tokens per session scan A 3cb3e49b00ca
backlog is a skill published in the GitHub repository umputun/agterm (677 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 2,024 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
orbit-linear
Open Orbit briefing skill — selected by the Orbit pipeline when Linear is the user's only connected connector, or when the user explicitly scopes their daily digest to Linear. Pulls the past 24 hours of issue movement, status changes, assignments, and cycle progress from the user's authenticated Linear connection and…
flowai-live-dashboard-template
Team-management dashboard skill in the FlowAI aesthetic — three tabs (Team Members, Team Details, Activity Log), KPI stat row, member table, role distribution bar chart, online presence and activity sparklines, and a top-contributors panel, all in a single self-contained HTML file with light/dark theming, hoverable…
handoff
Push the run's accepted artifact to a downstream collaboration surface (cli, other code agents, cloud, desktop) and stamp the artifact manifest with the export target.
kanban-board
Kanban / task board with columns (To do / In progress / In review / Done), draggable-looking cards, assignee avatars, swimlanes, and a top filter bar. Use when the brief mentions "kanban", "task board", "sprint board", "trello", "看板".
pm-spec
A one-page product specification, also called a PRD, that describes a problem, goals, success measures, user stories, scope, rollout stages, and open questions. A PRD is a planning document for building a product feature.
weekly-update
A single-file HTML slide deck for weekly team updates, covering shipped work, ongoing work, blockers, metrics, and requests. Slides use horizontal swiping or arrow and click navigation.