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 sigistry/marketplace --skill explain-interpretergit clone --depth 1 https://github.com/sigistry/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/sigistry/marketplace/explain-interpreter)<a href="https://agentmods.dev/skills/sigistry/marketplace/explain-interpreter"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/explain-interpreter/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/sigistry/marketplace/explain-interpreter"><img src="https://agentmods.dev/badge/skills/sigistry/marketplace/explain-interpreter.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 | $0.00095 | $0.01000 |
| Opus 5.5 | $0.00038 | $0.00400 |
| Sonnet 5.5 | $0.00019 | $0.00200 |
| Haiku 4.5 | $0.00010 | $0.00100 |
Grade A, and why
explain-interpreter 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Interpreter
Purpose
Provide a standardized way to read a query plan, Postgres or MySQL, text or JSON, and convert it into a plain-language diagnosis and a concrete fix, statically, from pasted output. A plan is a tree of nodes; the database executes the leaves first and passes rows up. The skill is knowing which node is actually eating the time and what that node's presence implies.
Reading methodology
- Identify the format and whether it was analyzed.
EXPLAINalone gives estimates;EXPLAIN ANALYZE(Postgres) /EXPLAIN ANALYZE(MySQL 8) gives actual rows, time, and loops. Only actuals prove a bad estimate. - Find the dominant node. Read inside-out. A node's cost/time includes its children, so compute self time = node time − children's time, and for inner nodes of a loop, multiply by
loops. The node with the largest self time (not the root) is the target. - Read the node's meaning (see
references/postgres-explain-nodes.md/references/mysql-explain.md). - Scan for red flags (below).
- Prescribe an index (right columns, right order) or a rewrite.
The single most important number: estimate vs actual
(cost=... rows=1000) is the planner's estimate; (actual ... rows=920000 loops=1) is reality. A large skew (planner thought 1 row, got 900k) means the planner chose the wrong strategy (often a nested loop that would have been a hash join). Causes: stale statistics (ANALYZE), correlated predicates the planner assumes independent, or expressions it cannot estimate. Fix the estimate and the plan often fixes itself.
Red-flag catalog
| Red flag | What the DB is doing | Fix |
|---|---|---|
Seq Scan / type: ALL on a big table with a selective WHERE |
Reading every row to find a few | Index the filter column |
rows estimate ≪ actual (loops) |
Planner mis-estimated → wrong join | ANALYZE; decorrelate; extended statistics |
Nested Loop with high inner loops |
Row-by-row inner lookups, N× | Index the inner join key; enable hash join |
Sort → Sort Method: external merge Disk |
Sort spilled to disk | Index matching ORDER BY; raise work_mem |
Using filesort / Using temporary (MySQL) |
Sorting/deduping without an index | Composite index over WHERE+ORDER BY |
Buffers: ... read≫hit |
Cold data, heavy I/O | Fewer rows scanned; covering index |
| Index exists but a Seq Scan is chosen | Predicate not sargable / type mismatch | Rewrite predicate; match types; expression index |
Wide width= with SELECT * in an index-only candidate |
Heap fetch forced | INCLUDE/covering columns |
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.
- 1mo ago First seen · 45 lines · 95 tokens per session scan A b2acb7ceb09e
explain-interpreter is a skill published in the GitHub repository sigistry/marketplace (3 stars, last pushed 10d ago), licensed MIT. It adds 95 tokens to every session and 1,000 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 2026-09-03.
Other skills, from other repositories
docker-dev-environment
Use when setting up local development services or running the project locally. Establishes the "stateful services in Docker, app runs native" pattern with Postgres, Redis, MinIO, and Mailpit.
ecto-patterns
Use when a task touches Ecto, even a how-to question: schemas, changesets, validations, queries, preloads, Multi, migrations, constraints, money fields. Load it before writing Ecto code. Skip for Ash.
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
cloudflare-hyperdrive
Cloudflare Hyperdrive for Workers-to-database connections with pooling and caching. Use for PostgreSQL/MySQL, Drizzle/Prisma, or encountering pool errors, TLS issues, connection refused.
ecto-constraint-debug
Debug Ecto constraint violations - trace triggers, check migrations, find duplicate data. Use when seeing uniqueconstraint, foreignkeyconstraint, or checkconstraint errors.
postgresql
PostgreSQL schema design, query optimization, indexing, and administration. Use when writing schemas, queries, migrations, or mentions PostgreSQL, Postgres, JSONB, partitioning, RLS, CTEs, window functions, EXPLAIN ANALYZE, or connection pooling.