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 Borda/vision-delivery --skill decompose-to-pipelinegit clone --depth 1 https://github.com/Borda/vision-deliveryWrote 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/borda/vision-delivery/decompose-to-pipeline)<a href="https://agentmods.dev/skills/borda/vision-delivery/decompose-to-pipeline"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/decompose-to-pipeline/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/borda/vision-delivery/decompose-to-pipeline"><img src="https://agentmods.dev/badge/skills/borda/vision-delivery/decompose-to-pipeline.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 | $0.00124 | $0.00928 |
| Opus 5 | $0.00062 | $0.00464 |
| Sonnet 5 | $0.00025 | $0.00186 |
| Haiku 4.5 | $0.00012 | $0.00093 |
Grade A, and why
decompose-to-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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translate a broad operational outcome into the smallest pipeline whose end-to-end decision clears independent acceptance. Optimize complexity or cost only after the end-to-end gate exists.
Platform execution boundary. Read ../../resources/roboflow-platform-lookup.md before any provider-specific lookup or action. Use installed official Roboflow skills or current MCP resources only for read-only discovery and sourced action-brief inputs; never invoke provider execution. Sentinel owns decomposition, contracts, evidence, and the go/revise/stop decision.
Follow ../../resources/fde-methodology.md for feasibility, frozen acceptance, consent, artifacts, and provenance.
1. Freeze the end-to-end decision
Inspect data, code, operating procedure, existing outputs, and cost/latency constraints. Describe one observable business decision, its input window, required output, action owner, and cost of a miss/false alarm. Create an acceptance ID before testing candidate components.
The gold set must be produced independently by a blinded human, sensor, or documented adjudication process. Candidate output and pseudo-label output are never ground truth. A pseudo-label model may bootstrap training examples only; measure/correct those examples on a blinded human-reviewed slice and exclude them from acceptance ownership.
2. Draw contracts, not brand names
Split the path into only necessary stages, for example:
capture -> perception -> deterministic transformation -> temporal aggregation -> business action
For each stage record input/output schema, units, error behavior, latency budget, data boundary, and owner. Keep deterministic arithmetic, geometry, filtering, validation, and business rules outside an expensive model when they are sufficient.
3. Establish the simplest baseline
Use recorded representative input and a replayable end-to-end harness. A baseline can combine current upstream candidates with local deterministic code, but exact upstream execution stays upstream. Record stage outputs so errors can be attributed. Measure the final business metric, not merely component accuracy.
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.
- 11d ago First seen · 77 lines · 124 tokens per session scan A b922e3cf7cb3
decompose-to-pipeline is a skill published in the GitHub repository Borda/vision-delivery (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 124 tokens to every session and 928 once invoked, about $0.0006 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 skills, from other repositories
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
pipeline
Use when the user asks to take a substantial feature from an initial idea through implementation in one mostly autonomous run.
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
setup
Use when superb's skills need their dependencies installed or checked — "set up superb", "install the dependencies", "why does pipeline say superpowers is missing", after a fresh plugin install, or on a new machine. Also use when a skill fails complaining that a superpowers sub-skill cannot be found.
boundedrelay-adaptive-sdd
Coordinate the optional BoundedRelay Spec Kit workflow with strict independent reviews, deterministic effort routing, bounded proposals, convergence, and handoff.