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 ijust/intent-planner --skill intent-db-designgit clone --depth 1 https://github.com/ijust/intent-plannerWrote 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/ijust/intent-planner/intent-db-design)<a href="https://agentmods.dev/skills/ijust/intent-planner/intent-db-design"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-db-design/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/ijust/intent-planner/intent-db-design"><img src="https://agentmods.dev/badge/skills/ijust/intent-planner/intent-db-design.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 | $0.00106 | $0.04205 |
| Opus 5.5 | $0.00042 | $0.01682 |
| Sonnet 5.5 | $0.00021 | $0.00841 |
| Haiku 4.5 | $0.00011 | $0.00421 |
Grade A, and why
intent-db-design 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
intent-db-design Skill
Core Mission
- Success Criteria:
- Starting from a single target packet responsible for designing a persistent data model, has read, read-only, the three layers — the target packet's intent / Scope, the compass's Invariants/Anti-direction, and the existing schema/migration (Grep) (R1.1)
- Has limited the input scope to a single target packet, the compass's Invariants/Anti-direction, and the existing schema/migration, and has not read the full Intent Tree or any out-of-scope packet (R1.3)
- Has produced a DB design (draft) including table definitions, constraints, indexes, and naming from the three-layer input (R1.2). When the existing schema cannot be identified by Grep (e.g., a new DB), has projected from intent and invariants alone, leaving the existing-schema input empty (R1.4)
- Attaches to each statement of the generated DB design a trace note showing its attribution to a projection source (target packet / compass invariant / existing schema), marks a statement attributable to none of them as
inferredand a statement whose existing schema could not be fully identified and thus could not be confirmed asunverified, and does not mix these with confirmed (source-derived) statements (R2.1 / R2.2). Has attributed every statement to one oftarget packet/compass invariant/existing schema/inferred/unverified(100% trace rate, R2.3) - Outputs in a structured form (
## Table:headings + column tables) that the downstream intent-validate can diff against the implementation schema (migration/DDL) on a per-item basis, in a shape where table definitions, constraints, indexes, and naming are identifiable as diffable units (R4.1 / R4.2) - Writes the output only as derived artifacts under
.intent/db-design/<packet-slug>/, and has not modified any canonical artifact (intent-tree / intent-compass / packets), the existing schema, or export drafts. Has not written the output into.intent/cc-sdd/,.intent/openspec/, or.intent/speckit/(export artifacts) (R3.1 / R3.2 / R3.3) - When the target packet can be uniquely identified by argument or by user confirmation, targets only that packet; when it cannot be identified, does not fill in the target by guessing but asks for a target specification and stops (R5.1 / R5.2). When part of the existing schema cannot be identified, uses only the identified range as input and reports that part could not be identified (R5.3)
- Has no wiring that auto-launches, runs a state machine, or invokes other skills; limits activation to a human's manual operation; and introduces no persistent store and connects to no external service at runtime (R6.4 / R6.5)
What ships with it
4 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.
- 2mo ago First seen · 93 lines · 106 tokens per session scan A 1a638bb0911b
intent-db-design is a skill published in the GitHub repository ijust/intent-planner (5 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 4,205 once invoked, about $0.0004 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.
Other skills, from other repositories
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
mongodb
Use when modeling MongoDB documents (embed versus reference, the 16MB cap, bucket and subset patterns), choosing or fixing indexes (compound order by the ESR rule, partial, TTL, multikey, reading explain), writing aggregation pipelines that stay index-eligible, running multi-document transactions with retry, or…
postgresdb
Use when PostgreSQL engine behaviour decides the answer — schema and type design, index choice, reading EXPLAIN on a slow query, zero-downtime DDL and backfills, or ops (roles, RLS, pooling, vacuum, partitioning, PITR). PG16, ORM-agnostic. NOT portable query logic (that is sql), NOT a managed provider's platform…
aws-essentials
Use when standing up the core AWS surface a small product needs: hardening a fresh account, a private S3 bucket, encrypted RDS Postgres, ECS Fargate vs EC2, CloudFront + OAC, or scoping an IAM policy to least privilege. NOT the CI pipeline that ships the container (that is deployment), NOT app-code access-control…
db-migrations
Use when a schema change must ship without downtime — NOT NULL, rename, type change, or backfilling millions of live rows — for the expand-contract sequence and the lock/batching discipline that keeps each step from freezing prod. NOT lock internals or EXPLAIN (that is postgresdb), NOT drizzle-kit mechanics (that is…
dynamodb
Use when modeling or operating a DynamoDB table: deriving partition/sort keys from access patterns, single-table vs table-per-entity, adding a GSI/LSI, on-demand vs provisioned capacity, or diagnosing hot-partition throttling. NOT relational schema/SQL/EXPLAIN (that is postgresdb), NOT aggregation-pipeline document…