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 agentmods add skills/packmindhub/coding-agents-matrix/add-agent-propertynpx skills add PackmindHub/coding-agents-matrix --skill add-agent-propertygit clone --depth 1 https://github.com/PackmindHub/coding-agents-matrixWrote 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/packmindhub/coding-agents-matrix/add-agent-property)<a href="https://agentmods.dev/skills/packmindhub/coding-agents-matrix/add-agent-property"><img src="https://agentmods.dev/badge/skills/packmindhub/coding-agents-matrix/add-agent-property.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00724 |
| Opus 5 | $0.00034 | $0.00362 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
add-agent-property 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Agent Property
Add a new property to the agents board by modifying four files in sequence.
Schema reference: See references/schema.md for data structures.
Workflow
1. Gather Property Details
Ask the user for:
- Property key (camelCase, e.g.,
contextWindow) - Display label (short, e.g., "Context Window")
- Tooltip description (1 sentence explaining the property)
- Cell type:
badge(yes/no/partial) ortext(free-form) - Group:
identity,packaging, orfeatures
2. Update agents-detailed.json
Add the property to every agent in src/data/agents-detailed.json:
"propertyKey": {
"value": null,
"detail": null
}
Insert after the last feature property, before additionalInfo.
3. Update groups.json
Add the property key to the appropriate group's columns array in src/data/groups.json:
{
"id": "features",
"label": "Features",
"columns": ["existingProp", "propertyKey"]
}
4. Update AgentTable.jsx
Add column definition to the columns array in src/components/AgentTable.jsx:
{ key: 'propertyKey', label: 'Label', sortable: true, cellType: 'badge', tooltip: 'Description' }
Insert at the position matching its group order.
5. Update useAgentsData.js
Add transformation in src/hooks/useAgentsData.js:
propertyKey: agent.propertyKey.value,
propertyKeyDetail: agent.propertyKey.detail,
6. Update FilterBar.jsx (for filterable properties)
If the property is in packaging or features group and has cellType: 'badge', add it to the featureOptions array in src/components/FilterBar.jsx:
{ key: 'propertyKey', label: 'Label' }
Insert in the appropriate section (Packaging or Features) following the existing order.
7. Update GitHub Issue Templates
01-update-agent.md - Add under Features section:
- [ ] **Property Label** (`propertyKey`)
- New value: <!-- yes/no/partial/null -->
- Detail:
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.
- 4d ago First seen · 98 lines · 67 tokens per session scan A b171e1ed50c6
add-agent-property is a skill published in the GitHub repository PackmindHub/coding-agents-matrix (19 stars, last pushed 4d ago), licensed Apache-2.0. It adds 67 tokens to every session and 724 once invoked, about $0.0003 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
lark-base
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、workflow、角色权限;遇到 Base/多维表格/bitable 或 /base/ 链接时使用。文件导入/导出转 lark-drive,认证/授权转 lark-shared。.
database-migration
Use when performing database schema changes, data migrations, large table modifications, or when zero-downtime deployment is required - guides systematic, reversible database changes with rollback planning.
naming-conventions
Enforce consistent naming conventions for variables, functions, files, and more. Use when the user names variables, functions, classes, files, database columns, or constants. Apply when reviewing code for naming consistency or when the user asks about naming best practices.
migration-patterns
Guide for database schema migrations with zero-downtime patterns, rollback strategies, data migrations, and migration testing. Use when the user writes database migrations, asks about schema changes in production, needs zero-downtime migration patterns, or plans rollback strategies. Trigger whenever database…
schema-design-guide
Guide for relational database schema design with normalization, indexing strategy, constraints, naming conventions, and denormalization tradeoffs. Use when the user designs database tables, asks about normalization, needs indexing advice, or defines foreign key relationships. Trigger whenever database schema, table…
query-optimization
Guide for optimizing SQL queries with EXPLAIN ANALYZE, index tuning, N+1 detection, covering indexes, and query plan analysis. Use when the user has slow database queries, asks about query performance, needs to interpret EXPLAIN output, or wants to eliminate N+1 queries. Trigger whenever query performance, slow…