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 larasrinath/bls_mcp --skill bls-querygit clone --depth 1 https://github.com/larasrinath/bls_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/larasrinath/bls_mcp/bls-query)<a href="https://agentmods.dev/skills/larasrinath/bls_mcp/bls-query"><img src="https://agentmods.dev/badge/skills/larasrinath/bls_mcp/bls-query/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/larasrinath/bls_mcp/bls-query"><img src="https://agentmods.dev/badge/skills/larasrinath/bls_mcp/bls-query.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 | $0.00062 | $0.00822 |
| Opus 5.5 | $0.00025 | $0.00329 |
| Sonnet 5.5 | $0.00012 | $0.00164 |
| Haiku 4.5 | $0.00006 | $0.00082 |
Grade A, and why
bls-query 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 2mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BLS Data Query
Instructions
When a user asks about U.S. economic/labor data, follow this workflow to resolve their query into the correct BLS series ID(s) and return accurate results.
Step 1: Identify the topic
Map the user's natural language to a BLS survey and series ID. Consult references/series-catalog.md for the full mapping of common topics to series IDs.
Common mappings:
- "CPI", "inflation", "consumer prices" --> CU survey, series
CUUR0000SA0(not seasonally adjusted) orCUSR0000SA0(seasonally adjusted) - "unemployment rate" --> LN survey, series
LNS14000000 - "jobs", "employment", "nonfarm payrolls" --> CE survey, series
CES0000000001 - "wages", "average hourly earnings" --> CE survey, series
CES0500000003 - "PPI", "producer prices" --> WP/PC survey
- "JOLTS", "job openings" --> JT survey, series
JTS000000000000000JOL
If the topic is ambiguous or you cannot confidently map it, use get_all_surveys to find the survey, then get_popular_series with the survey abbreviation to discover series IDs.
Step 2: Choose the right tool
| User intent | Tool | When to use |
|---|---|---|
| Latest value / current number | get_latest_series |
"What is the current...", "latest...", "most recent..." |
| Recent trend / time series | get_single_series |
"Show me CPI for the last few years", "trend in..." |
| Compare multiple indicators | get_multiple_series |
"Compare X and Y", multiple series needed |
| Explore what's available | get_all_surveys then get_popular_series |
"What data do you have on...", discovery questions |
| Details about a survey | get_survey |
"Tell me about the [survey name]" |
Step 3: Interpret and present results
- Always state the series ID used so the user can verify.
- Include the period (month/year) and value clearly.
- For CPI data, note whether it is seasonally adjusted or not.
- If the user asks about percent change or inflation rate, calculate it from the data if the
calculationsfield is not available (requires API key). - For unemployment, the value is already a percentage. For CPI, the value is an index number (base period 1982-84=100).
What ships with it
1 file 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.
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.
- 2mo ago First seen · 66 lines · 62 tokens per session scan A 7607b9b25528
bls-query is a skill published in the GitHub repository larasrinath/bls_mcp (1 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 822 once invoked, about $0.0002 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 2026-08-31.
bls-query compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bls-querylarasrinath/bls_mcp | Skill | 1 | 7mo ago | MIT | A | 62 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |