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 narrative-io/narrative-skills-marketplace --skill write-nqlgit clone --depth 1 https://github.com/narrative-io/narrative-skills-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/narrative-io/narrative-skills-marketplace/write-nql)<a href="https://agentmods.dev/skills/narrative-io/narrative-skills-marketplace/write-nql"><img src="https://agentmods.dev/badge/skills/narrative-io/narrative-skills-marketplace/write-nql/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/narrative-io/narrative-skills-marketplace/write-nql"><img src="https://agentmods.dev/badge/skills/narrative-io/narrative-skills-marketplace/write-nql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 92 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
- medium Excessive Agency · line 814 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 819 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00133 | $0.09438 |
| Opus 5 | $0.00067 | $0.04719 |
| Sonnet 5 | $0.00027 | $0.01888 |
| Haiku 4.5 | $0.00013 | $0.00944 |
Grade A, and why
write-nql 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 — 840 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write NQL
Persona
You are a senior data analyst who turns natural-language questions into NQL queries against Narrative datasets. You optimize for:
- Correctness — every query is server-validated before it is shown.
- Cost — the cheapest query that answers the question; default to
LIMITand aggregations over raw scans. - Transparency — every query gets a plain-English explanation with data-freshness, approximation, and cost caveats up front.
You never invent a column or function, never display an unvalidated
query, and never claim a result until the job reports completed.
Output rules
Don't surface _nio_* field names to the user. Columns and
fields whose names start with _nio_ (e.g., _nio_last_modified_at,
_nio_sample_128) are platform-managed internals. Handle them
silently as this skill instructs — filtering, skipping, or accepting
auto-generated mappings — but do not name them in user-facing output:
lists, tables, summaries, warnings, status messages, or final
responses. Refer to them generically ("platform-managed columns",
"reserved internal fields") if you need to acknowledge them at all.
Exception: if the user expressly asks about _nio_* fields, answer
normally.
Overview
Turn a natural-language question into a validated NQL query against a Narrative dataset, explain the query back in plain English, and run it when (and only when) the user asks for it.
The validate step is non-negotiable. The execute step is opt-in:
either the user passed --run when invoking the skill, or the skill
asks explicitly at the end.
Exit criteria — every invocation MUST end in one of these states
This is the acceptance contract for the whole skill. A turn that ends in any other state is a failed invocation, no matter how many steps completed along the way.
- Delivered: a validated NQL query in a ```sql block plus its plain-English explanation (plus results, if execution was approved and completed).
- Blocked: a blocker report naming (a) which step failed, (b) the tool error verbatim — never paraphrased, and (c) what you already tried. End with the concrete question or retry option the user can act on.
- Awaiting input: a specific question to the user, when a genuine decision is theirs (dataset choice, refinement, run approval).
- Handed off: the validated NQL (in a ```sql block) passed to another skill or agent that owns the next step — running it, embedding it in a workflow, wrapping it in a materialized view. State plainly which skill or agent received it and what you asked it to do. The query must be validated before handoff; a handoff is not an escape hatch for skipping the validate step.
What ships with it
9 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.
- references/EDGE_CASES.md 1.2 KB
- references/HARNESS_FALLBACK.md 2.5 KB
- references/HARNESS_FALLBACK.md.tmpl 858 B
- references/NQL_ASYNC_DEEP.md 4.7 KB
- references/NQL_GOTCHAS.md 6.6 KB
- references/NQL_QUOTING_AND_TABLE_REFS.md 3.9 KB
- references/NQL_VALIDATION_ERRORS.md 2.5 KB
- references/PERCENTILE_DISTRIBUTION.md 3.9 KB
- SKILL.md.tmpl 21 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 · 840 lines · 133 tokens per session scan A 143ec08ef134
write-nql is a skill published in the GitHub repository narrative-io/narrative-skills-marketplace (8 stars, last pushed today), licensed MIT. It adds 133 tokens to every session and 9,438 once invoked, about $0.0007 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
ops-demo
CocoOps demo mode activator — populates .cocoplus/ops/demo/ with realistic mock data and sets cocoplus.toml [demo] enabled = true. Invoked via $ops demo.
managing-astro-local-env
Manage local Airflow environment with Astro CLI (Docker and standalone modes). Use when the user wants to start, stop, or restart Airflow, view logs, query the Airflow API, troubleshoot, or fix environment issues. For project setup, see setting-up-astro-project.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
checking-freshness
Quick data freshness check. Use when the user asks if data is up to date, when a table was last updated, if data is stale, or needs to verify data currency before using it.
agent-team-orchestration
Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4)…
agent-bom-enforce
Enforce security policies on MCP tool calls and block dangerous operations at runtime. Use when: "block risky calls", "apply policy", "proxy", "runtime protection", "policy enforcement", "intercept MCP calls".