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 get-dx/dx-mcp-server --skill snapshot-summarygit clone --depth 1 https://github.com/get-dx/dx-mcp-serverWrote 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/get-dx/dx-mcp-server/snapshot-summary)<a href="https://agentmods.dev/skills/get-dx/dx-mcp-server/snapshot-summary"><img src="https://agentmods.dev/badge/skills/get-dx/dx-mcp-server/snapshot-summary/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/get-dx/dx-mcp-server/snapshot-summary"><img src="https://agentmods.dev/badge/skills/get-dx/dx-mcp-server/snapshot-summary.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 | $0.00086 | $0.02025 |
| Opus 5.5 | $0.00034 | $0.00810 |
| Sonnet 5.5 | $0.00017 | $0.00405 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
snapshot-summary 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Snapshot summary
Write a short summary of the latest completed snapshot for a leader. Lead with what matters. Do not just list the lowest scores against the benchmark.
1. Find the snapshots
Call listSnapshots(ordering="completed_at"). Ignore any snapshot with deleted_at set. The first remaining item is the latest snapshot. The second remaining item is the comparison snapshot. If the user names a different snapshot to compare against, use that one.
If there is only one snapshot, skip all comparisons and say so.
2. Collect data
Use compareSnapshotScores(snapshot_id, score_type, comparison_snapshot_id) for scores. It matches items by id, computes change, direction and vs_p_75, includes each item's distribution, and lists hidden and unmatched items separately. Prefer it over working these out by hand. If there is no comparison snapshot, call it without comparison_snapshot_id.
- Headline:
compareSnapshotScores(..., "dxi"). This returns one row per scale (dxi_five_point,dxi_three_point). Report the scale that has a score in both snapshots. - Drivers:
compareSnapshotScores(..., "driver"). - Workflows:
compareSnapshotScores(..., "workflow"). - Impact:
compareSnapshotScores(..., "impact"). Outcome measures such as Speed, Quality, Ease of delivery and Weekly time loss. Weekly time loss haslower_is_betterset. - Tools:
compareSnapshotScores(..., "csat"). Satisfaction with internal tools and processes. No benchmark. - Allocation:
compareSnapshotScores(..., "allocation"). One row per allocation item, with the percentage of time as the score. No benchmark, anddirectionis null because a shift is not better or worse on its own. - Comments:
getSnapshotComments(snapshot_id)for the latest snapshot. Follownext_cursorfor more pages. Group comments bydriver_name.
Scoping to a team
If the user asks about one team, or the request names a team, for example a manager asking about their own team, scope the scores to it. Find the team with listTeams, then pass its id as the team_ids filter to every compareSnapshotScores call. Team ids are stable across snapshots, so use them rather than snapshot team ids. Compare the team with the comparison snapshot, the org and the benchmarks, but keep the story about what that team can discuss and influence.
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.
- 2d ago First seen · 101 lines · 86 tokens per session scan A b06a423da561
snapshot-summary is a skill published in the GitHub repository get-dx/dx-mcp-server (13 stars, last pushed 2d ago), licensed MIT. It adds 86 tokens to every session and 2,025 once invoked, about $0.0003 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 2026-11-14.
snapshot-summary compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| snapshot-summaryget-dx/dx-mcp-server | Skill | 13 | 2d ago | MIT | A | 86 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 9d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chroniclemicrosoft/vscode | Skill | 195k | today | MIT | A | 72 | Claude Code, Codex |