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/colossus-lab/openarg_backend/debug-pipelinegit clone --depth 1 https://github.com/colossus-lab/openarg_backendWrote 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/colossus-lab/openarg_backend/debug-pipeline)<a href="https://agentmods.dev/commands/colossus-lab/openarg_backend/debug-pipeline"><img src="https://agentmods.dev/badge/commands/colossus-lab/openarg_backend/debug-pipeline.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 | $0.00000 | $0.01001 |
| Opus 5 | $0.00000 | $0.00500 |
| Sonnet 5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
debug-pipeline 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 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.
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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug backend pipeline: $ARGUMENTS
Diagnose the described problem in the scraper → embedding → collector → analyst pipeline. Follow this checklist:
Base infrastructure
- PostgreSQL running:
make db.upor check docker (docker ps | grep postgres) - Redis running: verify connectivity on port 6381
- Migrations applied:
make db.migrate - Environment variables:
OPENAI_API_KEY,DATABASE_URL,CELERY_BROKER_URL - Workers active: check in Flower (
make flower→ http://localhost:5556)
Scraper (src/app/infrastructure/celery/tasks/scraper_tasks.py)
-
scrape_catalog(portal)receives a valid portal (datos_gob_ar, caba, etc.) - The corresponding
IDataSourceadapter is registered in Dishka -
fetch_catalog()returnsCatalogEntry[]— is the CKAN portal responding? - Upsert to
datasetsworks (check UNIQUE constraint on source_id + portal) - Dispatches
index_dataset_embeddingfor each dataset - If failing: check worker-scraper logs, verify HTTPX timeout
Embedding (src/app/infrastructure/celery/tasks/embedding_tasks.py + scraper_tasks.py)
-
index_dataset_embedding(dataset_id)receives a valid UUID - The dataset exists in the
datasetstable - 3 chunks are generated: main, columns, contextual
- OpenAI embedding API responds (verify
OPENAI_API_KEY) - Chunks are saved in
dataset_chunkswith 1536-dim embedding - HNSW index works:
SELECT * FROM dataset_chunks ORDER BY embedding <=> $1 LIMIT 5 - If failing: check retries (max 3), review worker-embedding logs
Collector (src/app/infrastructure/celery/tasks/collector_tasks.py)
-
collect_dataset(dataset_id)downloads the file fromdownload_url - Format is supported (CSV, JSON, XLSX, XLS)
- Pandas parses correctly (check encoding, separators)
- Cache table
cache_{id}is created in PostgreSQL -
cached_datasetsis updated: status downloading → ready -
datasets.is_cached = trueandrow_countupdated - Row limit: 500k max
- If failing: check download URL, file format, worker-collector logs
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 · 83 lines · 0 tokens per session scan A f7e738043678
debug-pipeline is a command published in the GitHub repository colossus-lab/openarg_backend (143 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,001 tokens. 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 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.