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 lttr/claude-marketplace --skill insightsgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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/lttr/claude-marketplace/insights)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/insights"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/insights/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/lttr/claude-marketplace/insights"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/insights.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 | $0.00071 | $0.00592 |
| Opus 5 | $0.00036 | $0.00296 |
| Sonnet 5 | $0.00014 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
insights 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 11d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insights
Multi-op skill. Dispatch on first word of $ARGUMENTS.
Dispatch
| Op | First word | Reference |
|---|---|---|
| daily | daily [date] |
references/daily.md |
| weekly | weekly [date] |
references/weekly.md |
| catchup | catchup |
references/catchup.md |
| view | view (dashboard) |
references/view.md |
Empty / unknown → ask user.
Data Sources
| Source | Tool | Data |
|---|---|---|
| Azure PRs | az repos pr list |
PRs opened, merged, reviewed |
| Azure Work Items | az boards query |
Tickets started, completed, in progress |
| Local Git | git log |
Commits in current repo |
| Confluence | Atlassian MCP | Recently modified pages |
Workflow
- Parse op from
$ARGUMENTS - Read corresponding
references/<op>.md - Execute steps — collectors live in
${CLAUDE_SKILL_DIR}/collectors/, templates in${CLAUDE_SKILL_DIR}/templates/, dashboard in${CLAUDE_SKILL_DIR}/dashboard/
Prerequisites
az devops configure --defaults organization=https://dev.azure.com/YOUR_ORG project=YOUR_PROJECT
az login
Confluence integration: requires Atlassian MCP server. Skipped silently if absent.
Output Structure
.insights/
├── raw/
│ ├── prs.json # Azure PRs
│ ├── workitems.json # Azure work items
│ ├── commits.json # Local git commits
│ └── confluence.json # Confluence pages
├── 2025-01-08-insights.md # Daily reports
├── 2025-W02-insights.md # Weekly reports
└── dashboard.html # Generated dashboard
Notes
collectors/,templates/,dashboard/infra unchanged — only the dispatch surface consolidated.- Monthly review uses
collectors/format-review.mjs --month YYYY-MMor thetemplates/monthly-review.mdtemplate.
What ships with it
15 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.
- collectors/azure-prs.js 3.1 KB runs code
- collectors/azure-workitems.js 2.3 KB runs code
- collectors/filter-by-date.js 2.8 KB runs code
- collectors/format-review.mjs 6.8 KB runs code
- collectors/format-summary.js 3.2 KB runs code
- collectors/git-commits.js 1.5 KB runs code
- dashboard/generate.ts 5.5 KB runs code
- dashboard/template.html 23 KB
- references/catchup.md 1.2 KB
- references/daily.md 2.4 KB
- references/view.md 1.1 KB
- references/weekly.md 1.8 KB
- templates/daily-summary.md 2.3 KB
- templates/monthly-review.md 3.4 KB
- templates/weekly-summary.md 3.5 KB
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.
- 11d ago First seen · 63 lines · 71 tokens per session scan A 984125a2cd8e
insights is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 592 once invoked, about $0.0004 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
flow-next-land
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
share-a-library
Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
OCR Review-to-Approval Loop
Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…