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 commands/datathings/marketplace/backendgit clone --depth 1 https://github.com/datathings/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/commands/datathings/marketplace/backend)<a href="https://agentmods.dev/commands/datathings/marketplace/backend"><img src="https://agentmods.dev/badge/commands/datathings/marketplace/backend.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 | $0.00036 | $0.06685 |
| Opus 5 | $0.00018 | $0.03342 |
| Sonnet 5 | $0.00007 | $0.01337 |
| Haiku 4.5 | $0.00004 | $0.00668 |
Grade B, and why
backend scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
**Always confirm before wiping** — even in a full default run. `rm -rf gcdata` destroys the local graph; ask first (AskUserQuestion: wipe & run / run without wiping / skip the suite). If the user declines the wipe-and-ru Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Review & Cleanup
Purpose: One deep pass over the GCL backend across seven dimensions — dead code & duplication, anti-patterns, type safety, performance & concurrency, @expose API security/design, test coverage, best-practice gaps — followed by interactive cleanup. This is the single hub for backend quality (it replaces the old separate apicheck / typecheck / optimize / coverage commands).
Run After: each sprint, before releases, during refactors. Run when greycat lint already passes — every check here targets what the linter cannot see.
Companion: for the web UI use /greycat:frontend.
Scope — arguments: $ARGUMENTS
Default = everything. No upfront questions — resolve the scope from the arguments above and go. The only interactive moments are the gcdata-wipe confirm (Dimension 6) and the Cleanup menu at the end.
- Empty → run all seven dimensions.
help→ print the dimension table below (keyword + what it covers) and stop — do not run the review.- One or more keywords → run only those dimensions.
- Unknown keyword → print the dimension table, point out the bad keyword, and stop.
| Keyword | Dimension |
|---|---|
dead-code |
1 — Dead code & duplication |
antipatterns |
2 — Anti-patterns (correctness & safety) |
types |
3 — Type safety beyond lint |
perf |
4 — Performance & concurrency |
api |
5 — @expose API (security · performance · design) |
tests |
6 — Test coverage (always confirms before wiping gcdata) |
practices |
7 — Best-practice gaps |
Example: /greycat:backend api tests runs only Dimensions 5 + 6.
Any dimension not run — out of scope or a declined prerequisite — must appear in the Output as SKIPPED: <reason>, never silently omitted (a silent skip reads as "clean").
How to run this review — ultrathink + ultracode
Ultrathink (always). Reason deeply. State assumptions explicitly; when two readings exist (nodeIndex vs Map, persisted vs @volatile, plain fn service vs abstract type), name both and pick with a reason. Read lib/std/*.gcl for real examples instead of guessing by analogy. A finding you cannot tie to a concrete failure or a canonical rule is not a finding.
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 · 374 lines · 36 tokens per session scan B f1834996a5e0
backend is a command published in the GitHub repository datathings/marketplace (11 stars, last pushed 7d ago), licensed Apache-2.0. It adds 36 tokens to every session and 6,685 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.