Borrowing it
Nothing to install: this file belongs to radimsem/remindb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radimsem/remindb/dev/.claude/skills/add-store-query/SKILL.mdgit clone --depth 1 https://github.com/radimsem/remindbWrote 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/radimsem/remindb/add-store-query)<a href="https://agentmods.dev/skills/radimsem/remindb/add-store-query"><img src="https://agentmods.dev/badge/skills/radimsem/remindb/add-store-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/radimsem/remindb/add-store-query"><img src="https://agentmods.dev/badge/skills/radimsem/remindb/add-store-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 141 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00102 | $0.01997 |
| Opus 5.5 | $0.00041 | $0.00799 |
| Sonnet 5.5 | $0.00020 | $0.00399 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade A, and why
add-store-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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a query (and optionally a migration) to the store
pkg/store/ is the SQLite layer. Queries are SQL string constants in queries.go; methods on *Store execute them through s.Tx(...) for writes or s.db.QueryContext(...) for reads. Schema lives in migrations/000N_*.sql, embedded via embed.FS and applied at startup.
There are two workflows here. Pick the right one before you start.
Need new SQL only? ──> Workflow A (query)
Need a new column / table / index? ──> Workflow A + Workflow B (migration)
Workflow A — add a query and method
Three files. Same pattern every time.
| File | What changes |
|---|---|
pkg/store/queries.go |
Add a q<Verb><Noun> = ... const |
pkg/store/<domain>.go |
Add the method on *Store (temperature.go, node.go, search.go, snapshot.go — pick the matching domain) |
pkg/store/store_test.go |
Add a test that opens testutil.OpenTestDB(t) and exercises the method |
Query const
Constants are grouped at the bottom of queries.go next to related queries. Name them q<Verb><Noun> — e.g., qSelectColdNodes, qBoostTemperature, qIncrementAccess. No package prefix; the file is the namespace.
const qListSourceFiles = `SELECT DISTINCT source_file FROM nodes ORDER BY source_file`
For batch queries with a variable IN list, follow the qBoostTemperatureBatchPrefix pattern: define the prefix as a const, append placeholders + ) in the calling method.
Method shape
Two flavors based on read vs write.
Reads call s.db.QueryContext directly, defer rows.Close(), and return through collectRows (or a dedicated row-scanner if the columns differ from nodeColumns). Reads do not wrap in s.Tx(...).
func (s *Store) ListSourceFiles(ctx context.Context) ([]string, error) {
rows, err := s.db.QueryContext(ctx, qListSourceFiles)
if err != nil {
return nil, err
}
defer func() { _ = rows.Close() }()
var out []string
for rows.Next() {
var path string
if err := rows.Scan(&path); err != nil {
return nil, err
}
out = append(out, path)
}
return out, rows.Err()
}
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.
- 1mo ago First seen · 142 lines · 102 tokens per session scan A cfcb0097140d
add-store-query is a skill published in the GitHub repository radimsem/remindb (129 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,997 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 2026-08-30.
Other skills, from other repositories
sql-linting
Lint SQL with GoSQLX and explain its rules L001-L030 (whitespace, keyword case, comma placement, aliasing, plus safety, performance and naming rules), including which rules each entry point applies and which can be auto-fixed. Use when the user asks to lint SQL, enforce SQL style, explains a GoSQLX rule ID like L007…
sql-analysis
Full GoSQLX review of a SQL query or .sql file - syntax validity, statement types, referenced tables/columns/functions, injection patterns, style lint and a formatted version - followed by a plain-language explanation of what the SQL does and what to fix. Use when the user asks to analyze, review, check, explain or…
sql-security-review
SQL injection review with GoSQLX - scan SQL text for injection patterns (tautologies, UNION attacks, stacked queries, comment bypasses, time-based and out-of-band probes, dangerous functions) and review application code that builds SQL strings (concatenation, f-strings, fmt.Sprintf, template literals), recommending…
sql-dialects
Check whether SQL parses under a specific database dialect with GoSQLX (PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake, generic; MariaDB and ClickHouse via the CLI) and explain dialect-specific syntax problems. Use when the user asks if SQL is valid for a particular database, is porting SQL between…
sql-formatting
Format or pretty-print SQL with GoSQLX - consistent indentation, keyword casing and optional trailing semicolon. Use when the user asks to format, beautify, pretty-print, reindent or clean up SQL, or to make a .sql file consistent.
binder-modeling
Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.