Borrowing it
Nothing to install: this file belongs to banshee-data/velocity.report. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/banshee-data/velocity.report/main/.claude/skills/backlog-prune/SKILL.mdgit clone --depth 1 https://github.com/banshee-data/velocity.reportWrote 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/banshee-data/velocity.report/backlog-prune)<a href="https://agentmods.dev/skills/banshee-data/velocity.report/backlog-prune"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/backlog-prune/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/banshee-data/velocity.report/backlog-prune"><img src="https://agentmods.dev/badge/skills/banshee-data/velocity.report/backlog-prune.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 | $0.00040 | $0.02308 |
| Opus 5.5 | $0.00016 | $0.00923 |
| Sonnet 5.5 | $0.00008 | $0.00462 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
backlog-prune scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `One-line curl installer with platform detection` [S] ← already a separate item, confirm dedup How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: backlog-prune
Groom docs/BACKLOG.md. Covers three distinct passes:
- Completeness audit: every item in the Complete section must have a
[#NNN]PR number. - Theme coherence: read the next 5 point releases, identify theme drift and rebalancing opportunities.
- Size audit: flag L/XL items that should be split and propose candidate sub-tasks.
Usage
/backlog-prune
/backlog-prune --scan-all-prs
--scan-all-prs fetches each referenced PR from GitHub to verify it exists and is merged. Without the flag, only format is checked (no network calls).
Procedure
1. Read the backlog
cat docs/BACKLOG.md
Parse the file into two logical regions:
- Pending: all items above the
## Completeheading, grouped by their milestone section (### vX.Y.Z …). - Complete: all items under
## Complete.
2. Completeness audit (complete section)
For every line in the Complete section:
- Has PR: line begins with
[#NNN]where NNN is a positive integer. ✅ - Missing PR: line begins with
(#NNN)(issue-only),-with no bracket reference, or any other format. ❌
Collect all missing-PR items into a list.
If --scan-all-prs is set
For each [#NNN] reference found, fetch the PR to verify it is real and merged:
gh pr view NNN --json number,state,mergedAt --jq '[.number, .state, .mergedAt]'
Flag PRs that:
- Do not exist (gh exits non-zero)
- Are open (not yet merged)
- Are closed but not merged (abandoned)
Produce completeness report
## Completeness Audit
### Missing PR numbers (N items)
- Line NNN: "- (#381) …" — has issue reference only, needs [#PR]
- Line NNN: "- SSE backpressure …" — no reference at all
### PR verification (only with --scan-all-prs)
- #NNN: ✅ merged 2026-01-15
- #NNN: ❌ open — not yet merged
- #NNN: ❌ not found
If all complete items have valid [#NNN] references, write:
✅ All complete items carry a PR number.
3. Theme coherence (next 5 point releases)
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 · 247 lines · 40 tokens per session scan A 8374b58159f7
backlog-prune is a skill published in the GitHub repository banshee-data/velocity.report (11 stars, last pushed today), licensed Apache-2.0. It adds 40 tokens to every session and 2,308 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
backlog-prune compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| backlog-prunebanshee-data/velocity.report | Skill | 11 | today | Apache-2.0 | A | 40 | Claude Code |
| analyzing-network-traffic-for-incidentsmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 91 | Claude Code |
| analyzing-network-packets-with-scapymukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | A | 75 | Claude Code |
| analyzing-network-traffic-with-wiresharkmukul975/Anthropic-Cybersecurity-Skills | Skill | 36k | 2mo ago | Apache-2.0 | B | 49 | Claude Code |
| whitebox-toolsznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | A | 119 | Claude Code, Codex |
| performing-network-packet-capture-analysisxalgorix/xalgorix | Skill | 1.3k | yesterday | Apache-2.0 | C | 62 | Claude Code, Codex |
| pdalznlgis/opengis-skills | Skill | 76 | 10d ago | MIT | B | 90 | Claude Code, Codex |