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 rossumai/claude-marketplace --skill coupa-bulk-replicationgit clone --depth 1 https://github.com/rossumai/claude-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/rossumai/claude-marketplace/coupa-bulk-replication)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/coupa-bulk-replication"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/coupa-bulk-replication/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/rossumai/claude-marketplace/coupa-bulk-replication"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/coupa-bulk-replication.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Privilege Escalation · line 58 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Excessive Agency · line 29 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 255 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 285 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00032 | $0.13438 |
| Opus 5 | $0.00016 | $0.06719 |
| Sonnet 5 | $0.00006 | $0.02688 |
| Haiku 4.5 | $0.00003 | $0.01344 |
Grade A, and why
coupa-bulk-replication scanned grade A 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST "<org_url>/svc/master-data-hub/api/v1/dataset/<name>" \ How it starts
The opening of the file, as written. The whole thing — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coupa Bulk Replication
You are a Rossum.ai Solution Architect guiding the bulk replication of Coupa master data into Rossum Data Storage. This skill is for initial loads or re-seeding datasets that are too large for the standard Coupa Webhook Import hooks to handle within their timeout window.
Dataset or context: $ARGUMENTS
Safety: Remote API Confirmation Gate
- Present exactly what will be done — tool name, target environment, what gets created, changed, or deleted
- Wait for explicit user confirmation — do NOT batch multiple write operations into one approval
- Never proceed without a clear "yes" from the user
This applies to:
- Disabling or re-enabling import hooks (
rossum_patch_hook) - Creating, dropping, or renaming Data Storage collections
- Creating indexes on collections
- Running the replication script against a live environment
Read-only operations are fine without confirmation: listing hooks, listing collections, querying data storage, reading credentials, checking record counts.
If in doubt, confirm. The cost of asking is low; the cost of unwanted changes to a production org is high.
How to Use This Skill
This skill has 7 phases. Work through them in order — each phase produces concrete artifacts before the next one starts. Use tasks to track progress across phases so work can resume if interrupted.
| Phase | What it covers |
|---|---|
| 0 — Discovery | Credentials, token strategy, org URL, Coupa hook settings, dataset selection, --probe sizing + worker calibration (from previous run summaries when they exist) |
| 1 — Pre-flight | Disable hooks, create/clear collections, create indexes |
| 2 — Script Setup | Place coupa_bulk_import.py, create coupa_bulk_import.config.json, smoke-test |
| 3 — Replication | Supervised launch (--supervise, partitioned workers), keep-awake, monitoring, migration journal, resume |
| 4 — Completion | Verify counts, register with MDH |
| 5 — Handoff to continuous sync | Create or re-enable import hooks, delta seeding, canary |
| 6 — Debrief | Read run_summary.jsonl + journal, route learnings to their durable homes |
What ships with it
18 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.
- coupa_bulk_import.config.example.json 2.3 KB
- coupa_bulk_import.py 91 KB runs code
- tests/bulk_helpers.py 10 KB runs code
- tests/conftest.py 172 B runs code
- tests/test_bulk_cli_guards.py 6.2 KB runs code
- tests/test_bulk_config.py 3.9 KB runs code
- tests/test_bulk_dataset_arg.py 1.5 KB runs code
- tests/test_bulk_fetch.py 7.2 KB runs code
- tests/test_bulk_import_dataset.py 13 KB runs code
- tests/test_bulk_index_check.py 4.0 KB runs code
- tests/test_bulk_insert_batch.py 12 KB runs code
- tests/test_bulk_partitions.py 9.3 KB runs code
- tests/test_bulk_probe.py 7.4 KB runs code
- tests/test_bulk_rate_backoff.py 3.4 KB runs code
- tests/test_bulk_smoke.py 9.2 KB runs code
- tests/test_bulk_state.py 746 B runs code
- tests/test_bulk_supervise.py 15 KB runs code
- tests/test_bulk_token_reread.py 3.3 KB runs code
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.
- 12d ago First seen · 572 lines · 32 tokens per session scan A 18a83d3c314a
coupa-bulk-replication is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 13,438 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…