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 honeydew-ai/honeydew-ai-coding-agents-plugins --skill metric-creationgit clone --depth 1 https://github.com/honeydew-ai/honeydew-ai-coding-agents-pluginsWrote 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/honeydew-ai/honeydew-ai-coding-agents-plugins/metric-creation)<a href="https://agentmods.dev/skills/honeydew-ai/honeydew-ai-coding-agents-plugins/metric-creation"><img src="https://agentmods.dev/badge/skills/honeydew-ai/honeydew-ai-coding-agents-plugins/metric-creation/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/honeydew-ai/honeydew-ai-coding-agents-plugins/metric-creation"><img src="https://agentmods.dev/badge/skills/honeydew-ai/honeydew-ai-coding-agents-plugins/metric-creation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 findings, up to medium
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 →
- medium Prompt Injection · line 143 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 146 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 148 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 150 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 152 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 162 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 168 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 187 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Excessive Agency · line 297 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 | $0.00038 | $0.04050 |
| Opus 5 | $0.00019 | $0.02025 |
| Sonnet 5 | $0.00008 | $0.00810 |
| Haiku 4.5 | $0.00004 | $0.00405 |
Grade A, and why
metric-creation 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prerequisites
Before creating metrics, ensure you are on the correct workspace and branch. Use get_session_workspace_and_branch to check the current session context. For development work, create a branch with create_workspace_branch (the session switches automatically). See the workspace-branch skill for the full workspace/branch tool reference.
Overview
A Honeydew metric is a named, reusable aggregation anchored to an entity. Unlike a calculated attribute (which is per-row), a metric collapses multiple rows into a single value. Metrics are context-sensitive: they automatically respond to whatever filters and groupings the consuming BI tool or analyst applies.
Your job is to build an aggregation function that users can later group by.
If a user asks for a group by ("sum sales by category"), ignore the group. You're building the aggregation to sum sales by ANYTHING. The user will later use it in a query with their chosen dimensions.
Use a metric when:
- The same aggregation logic is reused across dashboards, teams, or tools
- You need a governed, single source of truth for a KPI (e.g. "revenue", "active users")
- The calculation involves combining other metrics (ratios, deltas)
Do not use a metric when the value is per-row (use a calculated attribute instead).
Building the SQL Expression
Core Rules
- MUST use an aggregation function — metrics collapse rows
- DO NOT use window functions — only aggregations allowed
- DO NOT use joins or subqueries — simple expressions only
- NEVER use COUNT(*) — use the entity's built-in count metric (e.g.,
entity.count) if available, orCOUNT(entity.key_field)on the primary key. NoDISTINCTneeded — primary keys are unique by definition. - Compose from existing metrics whenever possible. Honeydew accepts named metric references
(
entity.metric_name) anywhere you'd write a raw aggregation — insideFILTER (WHERE ...), insideGROUP BY (...)(both fixedGROUP BY (dim)and nestedGROUP BY (*, dim)), and as operands in derived arithmetic. Always check whether an existing metric can be the building block before reaching forSUM(...),COUNT(...), etc. The named-metric form expresses business intent, inherits future changes to the base metric, and keeps the model DRY. - For cross-entity counts, clarify intent first — filtered count or simple count. Use
related_entity.count FILTER (WHERE source_entity.key IS NOT NULL)for a filtered count. See reference.md "Cross-entity counts" for mechanics. - Reuse existing attributes — if a calculated attribute already exists (or you just created
one), reference it by name (e.g.,
entity.attribute_name) rather than repeating its SQL logic. - Use fully qualified column names —
entity.attribute, not justattribute
What ships with it
2 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.
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 · 306 lines · 38 tokens per session scan A 7f682464299b
metric-creation is a skill published in the GitHub repository honeydew-ai/honeydew-ai-coding-agents-plugins (39 stars, last pushed 11d ago), licensed Apache-2.0. It adds 38 tokens to every session and 4,050 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
sl
Skill "sl" from Kaelio/ktx, covering semantic layer, part 1 - schema reference, overlay sources, standalone table sources and standalone sql sources.
historic_sql_patterns
Identify recurring cross-table historic-SQL analytical intents from a bounded pattern shard and emit typed pattern evidence for deterministic wiki projection.