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 a-lottes/aSPARK --skill backloggit clone --depth 1 https://github.com/a-lottes/aSPARKWrote 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/a-lottes/aspark/backlog)<a href="https://agentmods.dev/skills/a-lottes/aspark/backlog"><img src="https://agentmods.dev/badge/skills/a-lottes/aspark/backlog/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/a-lottes/aspark/backlog"><img src="https://agentmods.dev/badge/skills/a-lottes/aspark/backlog.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 | $0.00094 | $0.01375 |
| Opus 5.5 | $0.00038 | $0.00550 |
| Sonnet 5.5 | $0.00019 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00137 |
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 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/backlog — Seed a Backlog from docs/ (Product Owner)
An advisory-then-writing ceremony with one gate. The Product Owner proposes
an ordered backlog from the project's own documents; the user edits it; only on
explicit confirmation are issues created. Nothing is written to .spark/, and
no spec is created here: specs belong to /story-time.
Input
Optional: --label <name> (repeatable) or a steer such as "only the MVP". No
other input is needed.
Steps
- Gather the sources yourself. The
product-owneragent cannot read the repo's remote or rungh. Read:docs/(Markdown/text documents only; read each section's heading and lead paragraph, not full bodies, and note file names and headings, as source references need them. Skip binary or non-text files and name what was skipped in the step 8 report),.spark/constitution.mdandROADMAP.mdif present.- If there is no
docs/(or it holds no readable documents) and no constitution, name/charteras the first step and stop there. Never invoke it yourself, and write nothing. Same rule as/next-steps.
- Delegate to the Product Owner. Invoke the
product-owneragent in its propose backlog mode (## Proposing a Backlogin its definition) with the document excerpts (file + section headings), the constitution excerpt or "none",ROADMAP.mdif present, and the user's steer. - Show the list as a plan. Present it as a numbered, ordered table: title,
problem statement, size (S/M/L), dependencies, source reference
docs/<file>#<section>. Drop any item that arrives without a source reference, or whose reference names no file and heading you gathered in step 1: nothing is invented. This check is an instruction to you and the agent, not an enforcement; look at every row yourself. - Let the user edit. They may drop, merge, reorder or reword items. Apply the edits (re-invoke the agent for merges/rewording if useful) and re-show the list. Repeat until the user confirms the final list or abandons it. Abandoning writes nothing.
- Resolve the repo and labels, once, before filing.
- Repo: from
origin(git remote get-url origin/gh repo view), as in/story-time. Echo the resolvedowner/repoto the user. No unambiguousorigin→ STOP and say so; never guess. - Labels: default none. Use labels passed as arguments; otherwise the
labels:list in the optional.spark/backlog.yml; arguments win. Echo them (or "no labels"). Apply them with--label; do not assume any particular automation behind them.
- Repo: from
- Ask for explicit confirmation to file, naming the count, repo and
labels. If the repo is public, say so here, once: the content of
docs/goes into the issue bodies. Only a yes in this conversation permits step 7. - File in order. For each item run
gh issue create --repo <owner/repo> --title '<title>' --body-file -(plus--labelper label), feeding the body on stdin from a single-quoted heredoc (<<'ASPARK_BACKLOG_BODY'). Never put text fromdocs/inside double quotes: the shell would run any backtick or$(...)in it. If any body line equals the delimiter, pick another one: that line would end the heredoc and the shell would run the rest. In the single-quoted title, write each'as'\''. Record each returned issue number; in later bodies, refer to dependencies already filed as#<n>, otherwise by title. The body is exactly:
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 First seen · 107 lines · 94 tokens per session scan A 7df2dfaeabf7
backlog is a skill published in the GitHub repository a-lottes/aSPARK (24 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,375 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 2026-10-26.
Other skills, from other repositories
tackle-issue
Start-of-work triage in this monorepo. Trigger on: a GitHub issue number ("tackle issue 99", "work on #42", bare #N), pasted proposal/spec text ("investigate this", "pressure-test this", "scope this"), or picker phrasing ("tackle the next issue", "what should I work on"). Read-only investigation that tries to falsify…
hermit-scribe
File a GitHub issue or post a comment on an existing issue via a GitHub App bot identity. Use when the operator says "file as a GH issue", "open an issue for PROP-NNN", "report this to the tracker", "add a comment to issue.
stale-proposals
Audit this repository's local proposal queue for stale entries: proposals still marked proposed, deferred, or accepted even though the work already shipped, plus old proposals whose subject has become inert. Reconcile proposals against plugin changelogs and first-parent Git history, automatically resolve only…
atlas-present
Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".
crest-narrative
Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", "planning memo", or "explain our product direction".
apex-status
CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done", or at the start of a work session.