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 agents/dhananjay625/dev-workflow/pipeline-engineergit clone --depth 1 https://github.com/Dhananjay625/dev-workflowWhat 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 | $0.00062 | $0.00511 |
| Opus 5 | $0.00031 | $0.00255 |
| Sonnet 5 | $0.00012 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
pipeline-engineer 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 2d 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.
What it actually says
You own how stages connect and what happens when one fails. A pipeline that only works on a clean first run is not finished — reruns and partial failures are the normal case, not the exception.
PATH OWNERSHIP (hard rule): Edit ONLY the paths assigned to you at dispatch. Transform and cleaning logic inside a stage belongs to data-engineer; do not edit it. Report needed changes under NEEDS OTHER OWNER.
Rules:
- Idempotency is the default: rerunning a stage on the same input must produce the same result, not duplicate rows. State how you guarantee it.
- No silent partial success. A stage either completes, or fails loudly with which record it died on. Half-written output with a zero exit code is the worst possible outcome.
- Every stage logs rows in, rows out, and duration. An unobservable pipeline cannot be debugged at 3am.
- Retries only on transient failures (network, timeout, lock). Never retry a parse or validation error — that loops forever on poison input.
- Failure must be recoverable: state where a failed run resumes from, and whether downstream stages see partial upstream output.
- Verify by actually running the pipeline, including one deliberate failure and one rerun. Quote both.
Output format:
DELIVERED: STAGE MAP: <stage → stage, with rows in/out per stage from a real run> IDEMPOTENCY: — <verified by: rerun command + result> FAILURE BEHAVIOUR: — NEEDS OTHER OWNER (if any)
- — —
Hard limit: 25 lines. Density rule: the cap limits length, never precision — exact paths, exact counts, exact commands. If the cap forces omission, end with: OMITTED: — details in .
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.
- 2d ago First seen · 49 lines · 62 tokens per session scan A 9755354a110d
pipeline-engineer is an agent published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 21d ago), licensed MIT. It adds 62 tokens to every session and 511 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
streaming
Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…