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 DelineaXPM/delinea-mcp --skill building-reportsgit clone --depth 1 https://github.com/DelineaXPM/delinea-mcpWrote 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/delineaxpm/delinea-mcp/building-reports)<a href="https://agentmods.dev/skills/delineaxpm/delinea-mcp/building-reports"><img src="https://agentmods.dev/badge/skills/delineaxpm/delinea-mcp/building-reports/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/delineaxpm/delinea-mcp/building-reports"><img src="https://agentmods.dev/badge/skills/delineaxpm/delinea-mcp/building-reports.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 | $0.00073 | $0.00892 |
| Opus 5.5 | $0.00029 | $0.00357 |
| Sonnet 5.5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
building-reports 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Secret Server reports
Secret Server answers analytic questions through SQL reports. The Delinea MCP server runs a report as a temporary report that it deletes afterwards, with the configured account's reporting permissions.
The tools named below come from the Delinea MCP server. Depending on how it
is installed, they may appear with a prefix such as mcp__delinea__.
Workflow
- Read the reference first. Call
list_example_reports. It returns tested example queries, the tables and columns they use, and special fields. Build every query from that reference. Don't guess table or column names. - Start from the closest example. Adapt an example query rather than
writing one from scratch. Keep its joins and
WITH (NOLOCK)hints. - Write a narrow query. Select only the columns the user needs, filter
with
WHERE, and aggregate (COUNT,GROUP BY) when the user asks "how many" or "which ones most". - Run it with
run_report. Pass a short, descriptivereport_name. Results are capped bymax_rows(default 200). Iftruncatedis true, refine the query or aggregate instead of raising the cap. - Check the result. Empty or surprising results usually mean a wrong join or filter. Re-check the reference and adjust before concluding.
- Present it. Show a table, or a summary with the key numbers, and say which filters you used. Offer the SQL if the user wants to save it as a permanent report in Secret Server.
SQL rules
- The database is Microsoft SQL Server (T-SQL). Use
SELECT TOP 50 ..., notLIMIT. UseGETDATE()andDATEADD(day, -90, GETDATE())for dates. - Only
SELECTstatements run. Don't attemptINSERT,UPDATE,DELETEor DDL. Make changes through the management tools instead. - Bracket reserved or spaced names:
[Permissions],[Role Permission]. - Report results pass through the conversation, so never select secret
values. Don't select
tbSecretItem.ItemValuefor password, key or token fields. To work with a credential, follow the no-secret-visibility skill. - Joining audit tables over long periods can be slow. Filter
DateRecordedto the window the user cares about.
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 · 66 lines · 73 tokens per session scan A 769bf5ab35d1
building-reports is a skill published in the GitHub repository DelineaXPM/delinea-mcp (50 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 892 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 2026-11-20.
building-reports compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| building-reportsDelineaXPM/delinea-mcp | Skill | 50 | yesterday | MIT | A | 73 | Claude Code |
| imagegenopenai/codex | Skill | 136k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 101k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 3d ago | MIT | A | 200 | Claude Code, Codex |
| browser-automationopenclaw/openclaw | Skill | 395k | today | MIT | A | 36 | Claude Code |
| free-llm-apismnfst/awesome-free-llm-apis | Skill | 14k | yesterday | CC0-1.0 | A | 113 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |